move it around

* Implement user input handling in Flow class

- Introduced `FlowInputRequestedEvent` and `FlowInputReceivedEvent` to manage user input requests and responses during flow execution.
- Added `InputProvider` protocol and `InputResponse` dataclass for customizable input handling.
- Enhanced `Flow` class with `ask()` method to request user input, including timeout handling and state checkpointing.
- Updated `FlowConfig` to support custom input providers.
- Created `input_provider.py` for default input provider implementations, including a console-based provider.
- Added comprehensive tests for `ask()` functionality, covering basic usage, timeout behavior, and integration with flow machinery.

* Potential fix for pull request finding 'Unused import'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* Refactor test_flow_ask.py to streamline flow kickoff calls

- Removed unnecessary variable assignments for the result of `flow.kickoff()` in two test cases, improving code clarity.
- Updated assertions to ensure the expected execution log entries are present after the flow kickoff, enhancing test reliability.

* Add current_flow_method_name context variable for flow method tracking

- Introduced a new context variable, `current_flow_method_name`, to store the name of the currently executing flow method, defaulting to "unknown".
- Updated the Flow class to set and reset this context variable during method execution, enhancing the ability to track method calls without stack inspection.
- Removed the obsolete `_resolve_calling_method_name` method, streamlining the code and improving clarity.

* Enhance input history management in Flow class

- Introduced a new `InputHistoryEntry` TypedDict to structure user input history for the `ask()` method, capturing details such as the question, user response, method name, timestamp, and associated metadata.
- Updated the `_input_history` attribute in the Flow class to utilize the new `InputHistoryEntry` type, improving type safety and clarity in input history management.

* Enhance timeout handling in Flow class input requests

- Updated the `ask()` method to improve timeout management by manually managing the `ThreadPoolExecutor`, preventing potential deadlocks when the provider call exceeds the timeout duration.
- Added clarifications in the documentation regarding the behavior of the timeout and the underlying request handling, ensuring better understanding for users.

* Enhance memory reset functionality in CLI commands

- Introduced flow memory reset capabilities in the `reset_memories_command`, allowing for both crew and flow memory resets.
- Added a new utility function `_reset_flow_memory` to handle memory resets for individual flow instances, improving modularity and clarity.
- Updated the `get_flows` utility to discover flow instances from project files, enhancing the CLI's ability to manage flow states.
- Expanded test coverage to validate the new flow memory reset features, ensuring robust functionality and error handling.

* LINTER

* Fix resumption flag logic in Flow class and add regression test for cyclic flow persistence

- Updated the logic for setting the `_is_execution_resuming` flag to ensure it only activates when there are completed methods to replay, preventing incorrect suppression of cyclic re-execution during state reloads.
- Added a regression test to validate that cyclic router flows complete all iterations when persistence is enabled and an 'id' is passed in inputs, ensuring robust handling of flow execution in these scenarios.

---------

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

.github/codeql/codeql-config.yml

@@ -14,13 +14,18 @@ paths-ignore:
   - "lib/crewai/src/crewai/experimental/a2a/**"
 
 paths:
+  # Include GitHub Actions workflows/composite actions for CodeQL actions analysis
+  - ".github/workflows/**"
+  - ".github/actions/**"
   # Include all Python source code from workspace packages
   - "lib/crewai/src/**"
   - "lib/crewai-tools/src/**"
+  - "lib/crewai-files/src/**"
   - "lib/devtools/src/**"
   # Include tests (but exclude cassettes via paths-ignore)
   - "lib/crewai/tests/**"
   - "lib/crewai-tools/tests/**"
+  - "lib/crewai-files/tests/**"
   - "lib/devtools/tests/**"
 
 # Configure specific queries or packs if needed

.github/workflows/codeql.yml

@@ -69,7 +69,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@v4
       with:
         languages: ${{ matrix.language }}
         build-mode: ${{ matrix.build-mode }}
@@ -98,6 +98,6 @@ jobs:
         exit 1
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@v4
       with:
         category: "/language:${{matrix.language}}"

.github/workflows/notify-downstream.yml

@@ -1,33 +0,0 @@
-name: Notify Downstream
-
-on:
-  push:
-    branches:
-      - main
-
-permissions:
-  contents: read
-
-jobs:
-  notify-downstream:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Generate GitHub App token
-        id: app-token
-        uses: tibdex/github-app-token@v2
-        with:
-          app_id: ${{ secrets.OSS_SYNC_APP_ID }}
-          private_key: ${{ secrets.OSS_SYNC_APP_PRIVATE_KEY }}
-
-      - name: Notify Repo B
-        uses: peter-evans/repository-dispatch@v3
-        with:
-          token: ${{ steps.app-token.outputs.token }}
-          repository: ${{ secrets.OSS_SYNC_DOWNSTREAM_REPO }}
-          event-type: upstream-commit
-          client-payload: |
-            {
-              "commit_sha": "${{ github.sha }}"
-            }
-

.gitignore

@@ -27,3 +27,6 @@ conceptual_plan.md
 build_image
 chromadb-*.lock
 .claude
+.crewai/memory
+blogs/*
+secrets/*

conftest.py

@@ -11,7 +11,11 @@ from typing import Any
 from dotenv import load_dotenv
 import pytest
 from vcr.request import Request  # type: ignore[import-untyped]
-import vcr.stubs.httpx_stubs as httpx_stubs  # type: ignore[import-untyped]
+
+try:
+    import vcr.stubs.httpx_stubs as httpx_stubs  # type: ignore[import-untyped]
+except ModuleNotFoundError:
+    import vcr.stubs.httpcore_stubs as httpx_stubs  # type: ignore[import-untyped]
 
 
 env_test_path = Path(__file__).parent / ".env.test"

docs/docs.json

@@ -79,6 +79,101 @@
                   "en/quickstart"
                 ]
               },
+              {
+                "group": "AI Docs",
+                "pages": [
+                  "en/ai/overview",
+                  {
+                    "group": "Flows",
+                    "icon": "arrow-progress",
+                    "pages": [
+                      "en/ai/flows/index",
+                      "en/ai/flows/reference",
+                      "en/ai/flows/patterns",
+                      "en/ai/flows/troubleshooting",
+                      "en/ai/flows/examples"
+                    ]
+                  },
+                  {
+                    "group": "Agents",
+                    "icon": "user",
+                    "pages": [
+                      "en/ai/agents/index",
+                      "en/ai/agents/reference",
+                      "en/ai/agents/patterns",
+                      "en/ai/agents/troubleshooting",
+                      "en/ai/agents/examples"
+                    ]
+                  },
+                  {
+                    "group": "Crews",
+                    "icon": "users",
+                    "pages": [
+                      "en/ai/crews/index",
+                      "en/ai/crews/reference",
+                      "en/ai/crews/patterns",
+                      "en/ai/crews/troubleshooting",
+                      "en/ai/crews/examples"
+                    ]
+                  },
+                  {
+                    "group": "LLMs",
+                    "icon": "microchip-ai",
+                    "pages": [
+                      "en/ai/llms/index",
+                      "en/ai/llms/reference",
+                      "en/ai/llms/patterns",
+                      "en/ai/llms/troubleshooting",
+                      "en/ai/llms/examples"
+                    ]
+                  },
+                  {
+                    "group": "Memory",
+                    "icon": "database",
+                    "pages": [
+                      "en/ai/memory/index",
+                      "en/ai/memory/reference",
+                      "en/ai/memory/patterns",
+                      "en/ai/memory/troubleshooting",
+                      "en/ai/memory/examples"
+                    ]
+                  },
+                  {
+                    "group": "Tools",
+                    "icon": "wrench",
+                    "pages": [
+                      "en/ai/tools/index",
+                      "en/ai/tools/reference",
+                      "en/ai/tools/patterns",
+                      "en/ai/tools/troubleshooting",
+                      "en/ai/tools/examples"
+                    ]
+                  }
+                ]
+              },
+              {
+                "group": "Core Concepts",
+                "pages": [
+                  "en/concepts/agents",
+                  "en/concepts/tasks",
+                  "en/concepts/crews",
+                  "en/concepts/flows",
+                  "en/concepts/production-architecture",
+                  "en/concepts/knowledge",
+                  "en/concepts/llms",
+                  "en/concepts/files",
+                  "en/concepts/processes",
+                  "en/concepts/collaboration",
+                  "en/concepts/training",
+                  "en/concepts/memory",
+                  "en/concepts/reasoning",
+                  "en/concepts/planning",
+                  "en/concepts/testing",
+                  "en/concepts/cli",
+                  "en/concepts/tools",
+                  "en/concepts/event-listener"
+                ]
+              },
               {
                 "group": "Guides",
                 "pages": [
@@ -111,6 +206,13 @@
                       "en/guides/flows/mastering-flow-state"
                     ]
                   },
+                  {
+                    "group": "Coding Tools",
+                    "icon": "terminal",
+                    "pages": [
+                      "en/guides/coding-tools/agents-md"
+                    ]
+                  },
                   {
                     "group": "Advanced",
                     "icon": "gear",
@@ -121,29 +223,6 @@
                   }
                 ]
               },
-              {
-                "group": "Core Concepts",
-                "pages": [
-                  "en/concepts/agents",
-                  "en/concepts/tasks",
-                  "en/concepts/crews",
-                  "en/concepts/flows",
-                  "en/concepts/production-architecture",
-                  "en/concepts/knowledge",
-                  "en/concepts/llms",
-                  "en/concepts/files",
-                  "en/concepts/processes",
-                  "en/concepts/collaboration",
-                  "en/concepts/training",
-                  "en/concepts/memory",
-                  "en/concepts/reasoning",
-                  "en/concepts/planning",
-                  "en/concepts/testing",
-                  "en/concepts/cli",
-                  "en/concepts/tools",
-                  "en/concepts/event-listener"
-                ]
-              },
               {
                 "group": "MCP Integration",
                 "pages": [
@@ -324,6 +403,7 @@
                   "en/learn/human-input-on-execution",
                   "en/learn/human-in-the-loop",
                   "en/learn/human-feedback-in-flows",
+                  "en/learn/flowstate-chat-history",
                   "en/learn/kickoff-async",
                   "en/learn/kickoff-for-each",
                   "en/learn/llm-connections",
@@ -476,7 +556,6 @@
               {
                 "group": "Examples",
                 "pages": [
-                  "en/examples/example",
                   "en/examples/cookbooks"
                 ]
               }
@@ -1475,6 +1554,18 @@
       "source": "/api-reference",
       "destination": "/en/api-reference/introduction"
     },
+    {
+      "source": "/",
+      "destination": "/en/introduction"
+    },
+    {
+      "source": "/en",
+      "destination": "/en/introduction"
+    },
+    {
+      "source": "/en/examples/example",
+      "destination": "/en/examples/cookbooks"
+    },
     {
       "source": "/introduction",
       "destination": "/en/introduction"

docs/en/ai/agents/examples.mdx

@@ -0,0 +1,12 @@
+---
+title: "Agents: Examples"
+description: "Runnable examples for robust agent configuration and execution."
+icon: "rocket-launch"
+mode: "wide"
+---
+
+## Example links
+
+- [/en/guides/agents/crafting-effective-agents](/en/guides/agents/crafting-effective-agents)
+- [/en/learn/customizing-agents](/en/learn/customizing-agents)
+- [/en/learn/coding-agents](/en/learn/coding-agents)

docs/en/ai/agents/index.mdx

@@ -0,0 +1,32 @@
+---
+title: "Agents: Concepts"
+description: "Agent role contracts, task boundaries, and decision criteria for robust agent behavior."
+icon: "user"
+mode: "wide"
+---
+
+## When to use
+
+- You need specialized behavior with explicit role and goal.
+- You need tool-enabled execution under constraints.
+
+## When not to use
+
+- Static transformations are enough without model reasoning.
+- Task can be solved by deterministic code only.
+
+## Core decisions
+
+| Decision | Choose this when |
+|---|---|
+| Single agent | Narrow scope, low coordination needs |
+| Multi-agent crew | Distinct expertise and review loops needed |
+| Tool-enabled agent | Model needs external actions or data |
+
+## Canonical links
+
+- Reference: [/en/ai/agents/reference](/en/ai/agents/reference)
+- Patterns: [/en/ai/agents/patterns](/en/ai/agents/patterns)
+- Troubleshooting: [/en/ai/agents/troubleshooting](/en/ai/agents/troubleshooting)
+- Examples: [/en/ai/agents/examples](/en/ai/agents/examples)
+- Existing docs: [/en/concepts/agents](/en/concepts/agents)

docs/en/ai/agents/patterns.mdx

@@ -0,0 +1,17 @@
+---
+title: "Agents: Patterns"
+description: "Practical agent patterns for role design, tool boundaries, and reliable outputs."
+icon: "diagram-project"
+mode: "wide"
+---
+
+## Patterns
+
+1. Role + reviewer pair
+- One agent drafts, one agent validates.
+
+2. Tool-bounded agent
+- Restrict tool list to minimal action set.
+
+3. Structured output agent
+- Force JSON or schema output for automation pipelines.

docs/en/ai/agents/reference.mdx

@@ -0,0 +1,22 @@
+---
+title: "Agents: Reference"
+description: "Reference for agent fields, prompt contracts, tool usage, and output constraints."
+icon: "book"
+mode: "wide"
+---
+
+## Agent contract
+
+- `role`: stable operating identity
+- `goal`: measurable completion objective
+- `backstory`: bounded style and context
+- `tools`: allowed action surface
+
+## Output contract
+
+- Prefer structured outputs for machine workflows.
+- Define failure behavior for missing tool data.
+
+## Canonical source
+
+Primary API details live in [/en/concepts/agents](/en/concepts/agents).

docs/en/ai/agents/troubleshooting.mdx

@@ -0,0 +1,12 @@
+---
+title: "Agents: Troubleshooting"
+description: "Diagnose and fix common agent reliability and instruction-following failures."
+icon: "circle-exclamation"
+mode: "wide"
+---
+
+## Common issues
+
+- Hallucinated tool results: require tool-call evidence in output.
+- Prompt drift: tighten role and success criteria.
+- Verbose but low-signal output: enforce concise schema output.

docs/en/ai/crews/examples.mdx

@@ -0,0 +1,12 @@
+---
+title: "Crews: Examples"
+description: "Runnable crew examples for sequential and hierarchical execution."
+icon: "rocket-launch"
+mode: "wide"
+---
+
+## Example links
+
+- [/en/guides/crews/first-crew](/en/guides/crews/first-crew)
+- [/en/learn/sequential-process](/en/learn/sequential-process)
+- [/en/learn/hierarchical-process](/en/learn/hierarchical-process)

docs/en/ai/crews/index.mdx

@@ -0,0 +1,26 @@
+---
+title: "Crews: Concepts"
+description: "When to use crews, process selection, delegation boundaries, and collaboration strategy."
+icon: "users"
+mode: "wide"
+---
+
+## When to use
+
+- You need multiple agents with specialized roles.
+- You need staged execution and reviewer loops.
+
+## Process decision table
+
+| Process | Best for |
+|---|---|
+| Sequential | Linear pipelines and deterministic ordering |
+| Hierarchical | Manager-controlled planning and delegation |
+
+## Canonical links
+
+- Reference: [/en/ai/crews/reference](/en/ai/crews/reference)
+- Patterns: [/en/ai/crews/patterns](/en/ai/crews/patterns)
+- Troubleshooting: [/en/ai/crews/troubleshooting](/en/ai/crews/troubleshooting)
+- Examples: [/en/ai/crews/examples](/en/ai/crews/examples)
+- Existing docs: [/en/concepts/crews](/en/concepts/crews)

docs/en/ai/crews/patterns.mdx

@@ -0,0 +1,12 @@
+---
+title: "Crews: Patterns"
+description: "Production crew patterns for decomposition, review loops, and hybrid orchestration with Flows."
+icon: "diagram-project"
+mode: "wide"
+---
+
+## Patterns
+
+1. Researcher + writer + reviewer
+2. Manager-directed hierarchical crew
+3. Flow-orchestrated multi-crew pipeline

docs/en/ai/crews/reference.mdx

@@ -0,0 +1,21 @@
+---
+title: "Crews: Reference"
+description: "Reference for crew composition, process semantics, task context passing, and execution modes."
+icon: "book"
+mode: "wide"
+---
+
+## Crew contract
+
+- `agents`: available executors
+- `tasks`: work units with expected output
+- `process`: ordering and delegation semantics
+
+## Runtime
+
+- `kickoff()` for synchronous runs
+- `kickoff_async()` for async execution
+
+## Canonical source
+
+Primary API details live in [/en/concepts/crews](/en/concepts/crews).

docs/en/ai/crews/troubleshooting.mdx

@@ -0,0 +1,12 @@
+---
+title: "Crews: Troubleshooting"
+description: "Common multi-agent coordination failures and practical fixes."
+icon: "circle-exclamation"
+mode: "wide"
+---
+
+## Common issues
+
+- Agents overlap on responsibilities: tighten role boundaries.
+- Output inconsistency: standardize expected outputs per task.
+- Slow runs: reduce unnecessary handoffs and model size.

docs/en/ai/flows/examples.mdx

@@ -0,0 +1,17 @@
+---
+title: "Flows: Examples"
+description: "Runnable end-to-end examples for production flow orchestration."
+icon: "rocket-launch"
+mode: "wide"
+---
+
+## Canonical examples
+
+<CardGroup cols={2}>
+  <Card title="Flowstate Chat History" icon="comments" href="/en/learn/flowstate-chat-history">
+    Persistent chat history with summary compaction and memory scope.
+  </Card>
+  <Card title="Flows Concepts Example" icon="arrow-progress" href="/en/concepts/flows">
+    Full API and feature-oriented flow examples, including routers and persistence.
+  </Card>
+</CardGroup>

docs/en/ai/flows/index.mdx

@@ -0,0 +1,39 @@
+---
+title: "Flows: Concepts"
+description: "When to use Flows, when not to use them, and key design constraints for production orchestration."
+icon: "arrow-progress"
+mode: "wide"
+---
+
+## When to use
+
+- You need deterministic orchestration, branching, and resumable execution.
+- You need explicit state transitions across steps.
+- You need persistence, routing, and event-driven control.
+
+## When not to use
+
+- A single prompt/response interaction is enough.
+- You only need one agent call without orchestration logic.
+
+## Core decisions
+
+| Decision | Choose this when |
+|---|---|
+| Unstructured state | Fast prototyping, highly dynamic fields |
+| Structured state | Stable contracts, team development, type safety |
+| `@persist()` | Long-running workflows and recovery requirements |
+| Router labels | Deterministic branch handling |
+
+## Canonical links
+
+- Reference: [/en/ai/flows/reference](/en/ai/flows/reference)
+- Patterns: [/en/ai/flows/patterns](/en/ai/flows/patterns)
+- Troubleshooting: [/en/ai/flows/troubleshooting](/en/ai/flows/troubleshooting)
+- Examples: [/en/ai/flows/examples](/en/ai/flows/examples)
+
+## Existing docs
+
+- [/en/concepts/flows](/en/concepts/flows)
+- [/en/guides/flows/mastering-flow-state](/en/guides/flows/mastering-flow-state)
+- [/en/learn/flowstate-chat-history](/en/learn/flowstate-chat-history)

docs/en/ai/flows/patterns.mdx

@@ -0,0 +1,29 @@
+---
+title: "Flows: Patterns"
+description: "Production flow patterns: triage routing, flowstate chat history, and human-in-the-loop checkpoints."
+icon: "diagram-project"
+mode: "wide"
+---
+
+## Recommended patterns
+
+1. Triage router flow
+- Inputs: normalized request payload
+- Output: deterministic route label + action
+- Reference: [/en/concepts/flows](/en/concepts/flows)
+
+2. Flowstate chat history
+- Inputs: `session_id`, `last_user_message`
+- Output: assistant reply + compact context state
+- Reference: [/en/learn/flowstate-chat-history](/en/learn/flowstate-chat-history)
+
+3. Human feedback gates
+- Inputs: generated artifact + reviewer feedback
+- Output: approved/rejected/revision path
+- Reference: [/en/learn/human-feedback-in-flows](/en/learn/human-feedback-in-flows)
+
+## Pattern requirements
+
+- declare explicit input schema
+- define expected output shape
+- list failure modes and retries

docs/en/ai/flows/reference.mdx

@@ -0,0 +1,34 @@
+---
+title: "Flows: Reference"
+description: "API-oriented reference for Flow decorators, lifecycle semantics, state, routing, and persistence."
+icon: "book"
+mode: "wide"
+---
+
+## Decorators
+
+- `@start()` entrypoint, optional conditional trigger
+- `@listen(...)` downstream method subscription
+- `@router(...)` label-based deterministic routing
+- `@persist()` automatic state persistence checkpoints
+
+## Runtime contracts
+
+- `kickoff(inputs=...)` initializes or updates run inputs.
+- final output is the value from the last completed method.
+- `self.state` always has an auto-generated `id`.
+
+## State contracts
+
+- Use typed state for durable workflows.
+- Keep control fields explicit (`route`, `status`, `retry_count`).
+- Avoid storing unbounded raw transcripts in state.
+
+## Resume and recovery
+
+- Use persistence for recoverable runs.
+- Keep idempotent step logic for safe retries.
+
+## Canonical source
+
+Primary API details live in [/en/concepts/flows](/en/concepts/flows).

docs/en/ai/flows/troubleshooting.mdx

@@ -0,0 +1,28 @@
+---
+title: "Flows: Troubleshooting"
+description: "Common flow failures, causes, and fixes for state, routing, persistence, and resumption."
+icon: "circle-exclamation"
+mode: "wide"
+---
+
+## Common issues
+
+### Branch did not trigger
+
+- Cause: router label mismatch.
+- Fix: align returned label with `@listen("label")` exactly.
+
+### State fields missing
+
+- Cause: untyped dynamic writes or missing inputs.
+- Fix: switch to typed state and validate required fields at `@start()`.
+
+### Context window blow-up
+
+- Cause: raw message accumulation.
+- Fix: use sliding window + summary compaction pattern.
+
+### Resume behavior inconsistent
+
+- Cause: non-idempotent side effects in retried steps.
+- Fix: make side-effecting calls idempotent and record execution markers in state.

docs/en/ai/llms/examples.mdx

@@ -0,0 +1,12 @@
+---
+title: "LLMs: Examples"
+description: "Concrete examples for model setup, routing, and output-control patterns."
+icon: "rocket-launch"
+mode: "wide"
+---
+
+## Example links
+
+- [/en/concepts/llms](/en/concepts/llms)
+- [/en/learn/llm-connections](/en/learn/llm-connections)
+- [/en/learn/custom-llm](/en/learn/custom-llm)

docs/en/ai/llms/index.mdx

@@ -0,0 +1,27 @@
+---
+title: "LLMs: Concepts"
+description: "Model selection strategy, cost-quality tradeoffs, and reliability posture for CrewAI systems."
+icon: "microchip-ai"
+mode: "wide"
+---
+
+## When to use advanced LLM configuration
+
+- You need predictable quality, latency, and cost control.
+- You need model routing by task type.
+
+## Core decisions
+
+| Decision | Choose this when |
+|---|---|
+| Single model | Small systems with uniform task profile |
+| Routed models | Mixed workloads with different quality/cost needs |
+| Structured output | Automation pipelines and strict parsing needs |
+
+## Canonical links
+
+- Reference: [/en/ai/llms/reference](/en/ai/llms/reference)
+- Patterns: [/en/ai/llms/patterns](/en/ai/llms/patterns)
+- Troubleshooting: [/en/ai/llms/troubleshooting](/en/ai/llms/troubleshooting)
+- Examples: [/en/ai/llms/examples](/en/ai/llms/examples)
+- Existing docs: [/en/concepts/llms](/en/concepts/llms)

docs/en/ai/llms/patterns.mdx

@@ -0,0 +1,17 @@
+---
+title: "LLMs: Patterns"
+description: "Model routing, reliability defaults, and structured outputs for production AI workflows."
+icon: "diagram-project"
+mode: "wide"
+---
+
+## Patterns
+
+1. Role-based model routing
+2. Reliability defaults (`timeout`, `max_retries`, low temperature)
+3. JSON-first outputs for machine consumption
+4. Responses API for multi-turn reasoning flows
+
+## Reference
+
+- [/en/concepts/llms#production-llm-patterns](/en/concepts/llms#production-llm-patterns)

docs/en/ai/llms/reference.mdx

@@ -0,0 +1,25 @@
+---
+title: "LLMs: Reference"
+description: "Provider-agnostic LLM configuration reference for CrewAI projects."
+icon: "book"
+mode: "wide"
+---
+
+## Common parameters
+
+- `model`
+- `temperature`
+- `max_tokens`
+- `timeout`
+- `max_retries`
+- `response_format`
+
+## Contract guidance
+
+- Set low temperature for extraction/classification.
+- Use structured outputs for downstream automation.
+- Set explicit timeout and retry policy for production.
+
+## Canonical source
+
+Primary API details live in [/en/concepts/llms](/en/concepts/llms).

docs/en/ai/llms/troubleshooting.mdx

@@ -0,0 +1,12 @@
+---
+title: "LLMs: Troubleshooting"
+description: "Fix common model behavior failures: drift, latency spikes, malformed output, and cost overruns."
+icon: "circle-exclamation"
+mode: "wide"
+---
+
+## Common issues
+
+- Malformed JSON: enforce `response_format` and validate at boundary.
+- Latency spikes: route heavy tasks to smaller models when acceptable.
+- Cost growth: add budget-aware model routing and truncation rules.

docs/en/ai/memory/examples.mdx

@@ -0,0 +1,11 @@
+---
+title: "Memory: Examples"
+description: "Runnable examples for scoped storage and semantic retrieval in CrewAI."
+icon: "rocket-launch"
+mode: "wide"
+---
+
+## Example links
+
+- [/en/concepts/memory](/en/concepts/memory)
+- [/en/learn/flowstate-chat-history](/en/learn/flowstate-chat-history)

docs/en/ai/memory/index.mdx

@@ -0,0 +1,24 @@
+---
+title: "Memory: Concepts"
+description: "Designing recall systems with scope boundaries and state-vs-memory separation."
+icon: "database"
+mode: "wide"
+---
+
+## When to use memory
+
+- You need semantic recall across runs.
+- You need long-term context outside immediate flow state.
+
+## When to use state instead
+
+- Data is only needed for current control flow.
+- Data must remain deterministic and explicit per step.
+
+## Canonical links
+
+- Reference: [/en/ai/memory/reference](/en/ai/memory/reference)
+- Patterns: [/en/ai/memory/patterns](/en/ai/memory/patterns)
+- Troubleshooting: [/en/ai/memory/troubleshooting](/en/ai/memory/troubleshooting)
+- Examples: [/en/ai/memory/examples](/en/ai/memory/examples)
+- Existing docs: [/en/concepts/memory](/en/concepts/memory)

docs/en/ai/memory/patterns.mdx

@@ -0,0 +1,17 @@
+---
+title: "Memory: Patterns"
+description: "Practical memory patterns for session recall, scoped retrieval, and hybrid flow-state designs."
+icon: "diagram-project"
+mode: "wide"
+---
+
+## Patterns
+
+1. Session-scoped recall (`/chat/{session_id}`)
+2. Project-scoped knowledge (`/project/{project_id}`)
+3. Hybrid pattern: flow state for control, memory for long-tail context
+
+## Reference
+
+- [/en/learn/flowstate-chat-history](/en/learn/flowstate-chat-history)
+- [/en/guides/flows/mastering-flow-state](/en/guides/flows/mastering-flow-state)

docs/en/ai/memory/reference.mdx

@@ -0,0 +1,23 @@
+---
+title: "Memory: Reference"
+description: "Reference for remember/recall contracts, scopes, and retrieval tuning."
+icon: "book"
+mode: "wide"
+---
+
+## API surface
+
+- `remember(content, scope=...)`
+- `recall(query, limit=...)`
+- `extract_memories(text)`
+- `scope(path)` and `subscope(name)`
+
+## Scope rules
+
+- use `/{entity_type}/{identifier}` paths
+- keep hierarchy shallow
+- isolate sessions by stable identifiers
+
+## Canonical source
+
+Primary API details live in [/en/concepts/memory](/en/concepts/memory).

docs/en/ai/memory/troubleshooting.mdx

@@ -0,0 +1,12 @@
+---
+title: "Memory: Troubleshooting"
+description: "Diagnose poor recall quality, scope leakage, and stale memory retrieval."
+icon: "circle-exclamation"
+mode: "wide"
+---
+
+## Common issues
+
+- Irrelevant recall: tighten scopes and query wording.
+- Missing recall: check scope path and recency weighting.
+- Scope leakage: avoid shared broad scopes for unrelated workflows.

docs/en/ai/overview.mdx

@@ -0,0 +1,54 @@
+---
+title: "AI-First Documentation"
+description: "Canonical, agent-optimized documentation map for Flows, Agents, Crews, LLMs, Memory, and Tools."
+icon: "sitemap"
+mode: "wide"
+---
+
+## Purpose
+
+This section is the canonical map for AI agents and developers.
+
+Use it when you need:
+- one source of truth per domain
+- predictable page structure
+- runnable patterns with explicit inputs and outputs
+
+## Domain Packs
+
+<CardGroup cols={3}>
+  <Card title="Flows" icon="arrow-progress" href="/en/ai/flows/index">
+    State, routing, persistence, resume, and orchestration lifecycle.
+  </Card>
+  <Card title="Agents" icon="user" href="/en/ai/agents/index">
+    Agent contracts, tool boundaries, prompt roles, and output discipline.
+  </Card>
+  <Card title="Crews" icon="users" href="/en/ai/crews/index">
+    Multi-agent execution, process choice, delegation, and coordination.
+  </Card>
+  <Card title="LLMs" icon="microchip-ai" href="/en/ai/llms/index">
+    Model configuration contracts, routing, reliability defaults, and providers.
+  </Card>
+  <Card title="Memory" icon="database" href="/en/ai/memory/index">
+    Retrieval semantics, scope design, and state-vs-memory architecture.
+  </Card>
+  <Card title="Tools" icon="wrench" href="/en/ai/tools/index">
+    Tool safety, schema contracts, retries, and integration patterns.
+  </Card>
+</CardGroup>
+
+## Writing Contract
+
+Every domain follows the same structure:
+1. Concepts (`index`)
+2. Reference (`reference`)
+3. Patterns (`patterns`)
+4. Troubleshooting (`troubleshooting`)
+5. Examples (`examples`)
+
+## Deprecation Policy
+
+When a page is replaced:
+- keep a redirect for the old URL
+- keep one canonical destination
+- avoid duplicated conceptual prose

docs/en/ai/tools/examples.mdx

@@ -0,0 +1,12 @@
+---
+title: "Tools: Examples"
+description: "Practical examples for tool-driven agents and crews."
+icon: "rocket-launch"
+mode: "wide"
+---
+
+## Example links
+
+- [/en/tools/overview](/en/tools/overview)
+- [/en/learn/create-custom-tools](/en/learn/create-custom-tools)
+- [/en/learn/tool-hooks](/en/learn/tool-hooks)

docs/en/ai/tools/index.mdx

@@ -0,0 +1,25 @@
+---
+title: "Tools: Concepts"
+description: "Tool selection strategy, safety boundaries, and reliability rules for agentic execution."
+icon: "wrench"
+mode: "wide"
+---
+
+## When to use tools
+
+- Agents need external data or side effects.
+- Deterministic systems must be integrated into agent workflows.
+
+## Tool safety rules
+
+- define clear input schemas
+- validate outputs before downstream use
+- isolate privileged tools behind policy checks
+
+## Canonical links
+
+- Reference: [/en/ai/tools/reference](/en/ai/tools/reference)
+- Patterns: [/en/ai/tools/patterns](/en/ai/tools/patterns)
+- Troubleshooting: [/en/ai/tools/troubleshooting](/en/ai/tools/troubleshooting)
+- Examples: [/en/ai/tools/examples](/en/ai/tools/examples)
+- Existing docs: [/en/concepts/tools](/en/concepts/tools)

docs/en/ai/tools/patterns.mdx

@@ -0,0 +1,12 @@
+---
+title: "Tools: Patterns"
+description: "Tool execution patterns for retrieval, action safety, and response grounding."
+icon: "diagram-project"
+mode: "wide"
+---
+
+## Patterns
+
+1. Read-first then write pattern
+2. Validation gate before side effects
+3. Fallback tool chains for degraded mode

docs/en/ai/tools/reference.mdx

@@ -0,0 +1,22 @@
+---
+title: "Tools: Reference"
+description: "Reference for tool invocation contracts, argument schemas, and runtime safeguards."
+icon: "book"
+mode: "wide"
+---
+
+## Tool contract
+
+- deterministic input schema
+- stable output schema
+- explicit error behavior
+
+## Runtime safeguards
+
+- timeout and retry policy
+- idempotency for side effects
+- validation before commit
+
+## Canonical source
+
+Primary API details live in [/en/concepts/tools](/en/concepts/tools).

docs/en/ai/tools/troubleshooting.mdx

@@ -0,0 +1,12 @@
+---
+title: "Tools: Troubleshooting"
+description: "Common tool-call failures and fixes for schema mismatch, retries, and side effects."
+icon: "circle-exclamation"
+mode: "wide"
+---
+
+## Common issues
+
+- Schema mismatch: align tool args with declared model output schema.
+- Repeated side effects: add idempotency keys.
+- Tool timeouts: define retries with bounded backoff.

docs/en/concepts/agents.mdx

@@ -23,6 +23,17 @@ In the CrewAI framework, an `Agent` is an autonomous unit that can:
   at creating content.
 </Tip>
 
+## When to Use Agents
+
+- You need role-specific reasoning and decision-making.
+- You need tool-enabled execution with delegated responsibilities.
+- You need reusable behavioral units across tasks and crews.
+
+## When Not to Use Agents
+
+- Deterministic business logic in plain code is sufficient.
+- A static transformation without reasoning is sufficient.
+
 <Note type="info" title="Enterprise Enhancement: Visual Agent Builder">
 CrewAI AMP includes a Visual Agent Builder that simplifies agent creation and configuration without writing code. Design your agents visually and test them in real-time.
 

docs/en/concepts/crews.mdx

@@ -9,6 +9,17 @@ mode: "wide"
 
 A crew in crewAI represents a collaborative group of agents working together to achieve a set of tasks. Each crew defines the strategy for task execution, agent collaboration, and the overall workflow.
 
+## When to Use Crews
+
+- You need multiple specialized agents collaborating on a shared outcome.
+- You need process-level orchestration (`sequential` or `hierarchical`).
+- You need task-level handoffs and context propagation.
+
+## When Not to Use Crews
+
+- A single agent can complete the work end-to-end.
+- You do not need multi-step task decomposition.
+
 ## Crew Attributes
 
 | Attribute                             | Parameters             | Description                                                                                                                                                                                                                                               |
@@ -417,3 +428,17 @@ crewai replay -t <task_id>
 ```
 
 These commands let you replay from your latest kickoff tasks, still retaining context from previously executed tasks.
+
+## Common Failure Modes
+
+### Agents overlap responsibilities
+- Cause: role/goal definitions are too broad.
+- Fix: tighten role boundaries and task ownership.
+
+### Hierarchical runs stall or degrade
+- Cause: weak manager configuration or unclear delegation criteria.
+- Fix: define a stronger manager objective and explicit completion criteria.
+
+### Crew outputs are inconsistent
+- Cause: expected outputs are underspecified across tasks.
+- Fix: enforce structured outputs and stronger task contracts.

docs/en/concepts/flows.mdx

@@ -19,82 +19,121 @@ Flows allow you to create structured, event-driven workflows. They provide a sea
 
 4. **Flexible Control Flow**: Implement conditional logic, loops, and branching within your workflows.
 
+## When to Use Flows
+
+- You need deterministic orchestration and branching logic.
+- You need explicit state transitions across multiple steps.
+- You need resumable workflows with persistence.
+- You need to combine crews, direct model calls, and Python logic in one runtime.
+
+## When Not to Use Flows
+
+- A single prompt/response call is sufficient.
+- A single crew kickoff with no orchestration logic is sufficient.
+- You do not need stateful multi-step execution.
+
 ## Getting Started
 
-Let's create a simple Flow where you will use OpenAI to generate a random city in one task and then use that city to generate a fun fact in another task.
+The example below shows a realistic Flow for support-ticket triage. It demonstrates features teams use in production: typed state, routing, memory access, and persistence.
 
 ```python Code
-
-from crewai.flow.flow import Flow, listen, start
-from dotenv import load_dotenv
-from litellm import completion
+from crewai.flow.flow import Flow, listen, router, start
+from crewai.flow.persistence import persist
+from pydantic import BaseModel, Field
 
 
-class ExampleFlow(Flow):
-    model = "gpt-4o-mini"
+class SupportTriageState(BaseModel):
+    ticket_id: str = ""
+    customer_tier: str = "standard"  # standard | enterprise
+    issue: str = ""
+    urgency: str = "normal"
+    route: str = ""
+    draft_reply: str = ""
+    internal_notes: list[str] = Field(default_factory=list)
 
+
+@persist()
+class SupportTriageFlow(Flow[SupportTriageState]):
     @start()
-    def generate_city(self):
-        print("Starting flow")
-        # Each flow state automatically gets a unique ID
-        print(f"Flow State ID: {self.state['id']}")
+    def ingest_ticket(self):
+        # kickoff(inputs={...}) is merged into typed state fields
+        print(f"Flow State ID: {self.state.id}")
 
-        response = completion(
-            model=self.model,
-            messages=[
-                {
-                    "role": "user",
-                    "content": "Return the name of a random city in the world.",
-                },
-            ],
+        self.remember(
+            f"Ticket {self.state.ticket_id}: {self.state.issue}",
+            scope=f"/support/{self.state.ticket_id}",
         )
 
-        random_city = response["choices"][0]["message"]["content"]
-        # Store the city in our state
-        self.state["city"] = random_city
-        print(f"Random City: {random_city}")
+        issue = self.state.issue.lower()
+        if "security" in issue or "breach" in issue:
+            self.state.urgency = "critical"
+        elif self.state.customer_tier == "enterprise":
+            self.state.urgency = "high"
+        else:
+            self.state.urgency = "normal"
 
-        return random_city
+        return self.state.issue
 
-    @listen(generate_city)
-    def generate_fun_fact(self, random_city):
-        response = completion(
-            model=self.model,
-            messages=[
-                {
-                    "role": "user",
-                    "content": f"Tell me a fun fact about {random_city}",
-                },
-            ],
+    @router(ingest_ticket)
+    def route_ticket(self):
+        issue = self.state.issue.lower()
+        if "security" in issue or "breach" in issue:
+            self.state.route = "security"
+            return "security_review"
+        if self.state.customer_tier == "enterprise" or self.state.urgency == "high":
+            self.state.route = "priority"
+            return "priority_queue"
+        self.state.route = "standard"
+        return "standard_queue"
+
+    @listen("security_review")
+    def handle_security(self):
+        self.state.internal_notes.append("Escalated to Security Incident Response")
+        self.state.draft_reply = (
+            "We have escalated your case to our security team and will update you shortly."
         )
+        return self.state.draft_reply
 
-        fun_fact = response["choices"][0]["message"]["content"]
-        # Store the fun fact in our state
-        self.state["fun_fact"] = fun_fact
-        return fun_fact
+    @listen("priority_queue")
+    def handle_priority(self):
+        history = self.recall("SLA commitments for enterprise support", limit=2)
+        self.state.internal_notes.append(
+            f"Loaded {len(history)} memory hits for priority handling"
+        )
+        self.state.draft_reply = (
+            "Your ticket has been prioritized and assigned to a senior support engineer."
+        )
+        return self.state.draft_reply
+
+    @listen("standard_queue")
+    def handle_standard(self):
+        self.state.internal_notes.append("Routed to standard support queue")
+        self.state.draft_reply = "Thanks for reporting this. Our team will follow up soon."
+        return self.state.draft_reply
 
 
-
-flow = ExampleFlow()
-flow.plot()
-result = flow.kickoff()
-
-print(f"Generated fun fact: {result}")
+flow = SupportTriageFlow()
+flow.plot("support_triage_flow")
+result = flow.kickoff(
+    inputs={
+        "ticket_id": "TCK-1024",
+        "customer_tier": "enterprise",
+        "issue": "Cannot access SSO after enabling new policy",
+    }
+)
+print("Final reply:", result)
+print("Route:", flow.state.route)
+print("Notes:", flow.state.internal_notes)
 ```
 ![Flow Visual image](/images/crewai-flow-1.png)
-In the above example, we have created a simple Flow that generates a random city using OpenAI and then generates a fun fact about that city. The Flow consists of two tasks: `generate_city` and `generate_fun_fact`. The `generate_city` task is the starting point of the Flow, and the `generate_fun_fact` task listens for the output of the `generate_city` task.
+In this example, one flow demonstrates several core features together:
+1. `@start()` initializes and normalizes state for downstream steps.
+2. `@router()` performs deterministic branching into labeled routes.
+3. Route listeners implement lane-specific behavior (`security`, `priority`, `standard`).
+4. `@persist()` keeps the flow state recoverable between runs.
+5. Built-in memory methods (`remember`, `recall`) add durable context beyond a single method call.
 
-Each Flow instance automatically receives a unique identifier (UUID) in its state, which helps track and manage flow executions. The state can also store additional data (like the generated city and fun fact) that persists throughout the flow's execution.
-
-When you run the Flow, it will:
-1. Generate a unique ID for the flow state
-2. Generate a random city and store it in the state
-3. Generate a fun fact about that city and store it in the state
-4. Print the results to the console
-
-The state's unique ID and stored data can be useful for tracking flow executions and maintaining context between tasks.
-
-**Note:** Ensure you have set up your `.env` file to store your `OPENAI_API_KEY`. This key is necessary for authenticating requests to the OpenAI API.
+This pattern mirrors typical production workflows where request classification, policy-aware routing, and auditable state all happen in one orchestrated flow.
 
 ### @start()
 
@@ -117,15 +156,15 @@ The `@listen()` decorator can be used in several ways:
 1. **Listening to a Method by Name**: You can pass the name of the method you want to listen to as a string. When that method completes, the listener method will be triggered.
 
    ```python Code
-   @listen("generate_city")
-   def generate_fun_fact(self, random_city):
+   @listen("upstream_method")
+   def downstream_method(self, upstream_result):
        # Implementation
    ```
 
 2. **Listening to a Method Directly**: You can pass the method itself. When that method completes, the listener method will be triggered.
    ```python Code
-   @listen(generate_city)
-   def generate_fun_fact(self, random_city):
+   @listen(upstream_method)
+   def downstream_method(self, upstream_result):
        # Implementation
    ```
 
@@ -741,201 +780,17 @@ This example demonstrates several key features of using Agents in flows:
 
 3. **Tool Integration**: Agents can use tools (like `WebsiteSearchTool`) to enhance their capabilities.
 
-## Adding Crews to Flows
+## Multi-Crew Flows and Plotting
 
-Creating a flow with multiple crews in CrewAI is straightforward.
+Detailed build walkthroughs and project scaffolding are documented in guide pages to keep this concepts page focused.
 
-You can generate a new CrewAI project that includes all the scaffolding needed to create a flow with multiple crews by running the following command:
+- Build your first flow: [/en/guides/flows/first-flow](/en/guides/flows/first-flow)
+- Master state and persistence: [/en/guides/flows/mastering-flow-state](/en/guides/flows/mastering-flow-state)
+- Real-world chat-state pattern: [/en/learn/flowstate-chat-history](/en/learn/flowstate-chat-history)
 
-```bash
-crewai create flow name_of_flow
-```
-
-This command will generate a new CrewAI project with the necessary folder structure. The generated project includes a prebuilt crew called `poem_crew` that is already working. You can use this crew as a template by copying, pasting, and editing it to create other crews.
-
-### Folder Structure
-
-After running the `crewai create flow name_of_flow` command, you will see a folder structure similar to the following:
-
-| Directory/File         | Description                                                        |
-| :--------------------- | :----------------------------------------------------------------- |
-| `name_of_flow/`        | Root directory for the flow.                                       |
-| ├── `crews/`           | Contains directories for specific crews.                           |
-| │ └── `poem_crew/`     | Directory for the "poem_crew" with its configurations and scripts. |
-| │ ├── `config/`        | Configuration files directory for the "poem_crew".                 |
-| │ │ ├── `agents.yaml`  | YAML file defining the agents for "poem_crew".                     |
-| │ │ └── `tasks.yaml`   | YAML file defining the tasks for "poem_crew".                      |
-| │ ├── `poem_crew.py`   | Script for "poem_crew" functionality.                              |
-| ├── `tools/`           | Directory for additional tools used in the flow.                   |
-| │ └── `custom_tool.py` | Custom tool implementation.                                        |
-| ├── `main.py`          | Main script for running the flow.                                  |
-| ├── `README.md`        | Project description and instructions.                              |
-| ├── `pyproject.toml`   | Configuration file for project dependencies and settings.          |
-| └── `.gitignore`       | Specifies files and directories to ignore in version control.      |
-
-### Building Your Crews
-
-In the `crews` folder, you can define multiple crews. Each crew will have its own folder containing configuration files and the crew definition file. For example, the `poem_crew` folder contains:
-
-- `config/agents.yaml`: Defines the agents for the crew.
-- `config/tasks.yaml`: Defines the tasks for the crew.
-- `poem_crew.py`: Contains the crew definition, including agents, tasks, and the crew itself.
-
-You can copy, paste, and edit the `poem_crew` to create other crews.
-
-### Connecting Crews in `main.py`
-
-The `main.py` file is where you create your flow and connect the crews together. You can define your flow by using the `Flow` class and the decorators `@start` and `@listen` to specify the flow of execution.
-
-Here's an example of how you can connect the `poem_crew` in the `main.py` file:
-
-```python Code
-#!/usr/bin/env python
-from random import randint
-
-from pydantic import BaseModel
-from crewai.flow.flow import Flow, listen, start
-from .crews.poem_crew.poem_crew import PoemCrew
-
-class PoemState(BaseModel):
-    sentence_count: int = 1
-    poem: str = ""
-
-class PoemFlow(Flow[PoemState]):
-
-    @start()
-    def generate_sentence_count(self):
-        print("Generating sentence count")
-        self.state.sentence_count = randint(1, 5)
-
-    @listen(generate_sentence_count)
-    def generate_poem(self):
-        print("Generating poem")
-        result = PoemCrew().crew().kickoff(inputs={"sentence_count": self.state.sentence_count})
-
-        print("Poem generated", result.raw)
-        self.state.poem = result.raw
-
-    @listen(generate_poem)
-    def save_poem(self):
-        print("Saving poem")
-        with open("poem.txt", "w") as f:
-            f.write(self.state.poem)
-
-def kickoff():
-    poem_flow = PoemFlow()
-    poem_flow.kickoff()
-
-
-def plot():
-    poem_flow = PoemFlow()
-    poem_flow.plot("PoemFlowPlot")
-
-if __name__ == "__main__":
-    kickoff()
-    plot()
-```
-
-In this example, the `PoemFlow` class defines a flow that generates a sentence count, uses the `PoemCrew` to generate a poem, and then saves the poem to a file. The flow is kicked off by calling the `kickoff()` method. The PoemFlowPlot will be generated by `plot()` method.
-
-![Flow Visual image](/images/crewai-flow-8.png)
-
-### Running the Flow
-
-(Optional) Before running the flow, you can install the dependencies by running:
-
-```bash
-crewai install
-```
-
-Once all of the dependencies are installed, you need to activate the virtual environment by running:
-
-```bash
-source .venv/bin/activate
-```
-
-After activating the virtual environment, you can run the flow by executing one of the following commands:
-
-```bash
-crewai flow kickoff
-```
-
-or
-
-```bash
-uv run kickoff
-```
-
-The flow will execute, and you should see the output in the console.
-
-## Plot Flows
-
-Visualizing your AI workflows can provide valuable insights into the structure and execution paths of your flows. CrewAI offers a powerful visualization tool that allows you to generate interactive plots of your flows, making it easier to understand and optimize your AI workflows.
-
-### What are Plots?
-
-Plots in CrewAI are graphical representations of your AI workflows. They display the various tasks, their connections, and the flow of data between them. This visualization helps in understanding the sequence of operations, identifying bottlenecks, and ensuring that the workflow logic aligns with your expectations.
-
-### How to Generate a Plot
-
-CrewAI provides two convenient methods to generate plots of your flows:
-
-#### Option 1: Using the `plot()` Method
-
-If you are working directly with a flow instance, you can generate a plot by calling the `plot()` method on your flow object. This method will create an HTML file containing the interactive plot of your flow.
-
-```python Code
-# Assuming you have a flow instance
-flow.plot("my_flow_plot")
-```
-
-This will generate a file named `my_flow_plot.html` in your current directory. You can open this file in a web browser to view the interactive plot.
-
-#### Option 2: Using the Command Line
-
-If you are working within a structured CrewAI project, you can generate a plot using the command line. This is particularly useful for larger projects where you want to visualize the entire flow setup.
-
-```bash
-crewai flow plot
-```
-
-This command will generate an HTML file with the plot of your flow, similar to the `plot()` method. The file will be saved in your project directory, and you can open it in a web browser to explore the flow.
-
-### Understanding the Plot
-
-The generated plot will display nodes representing the tasks in your flow, with directed edges indicating the flow of execution. The plot is interactive, allowing you to zoom in and out, and hover over nodes to see additional details.
-
-By visualizing your flows, you can gain a clearer understanding of the workflow's structure, making it easier to debug, optimize, and communicate your AI processes to others.
-
-### Conclusion
-
-Plotting your flows is a powerful feature of CrewAI that enhances your ability to design and manage complex AI workflows. Whether you choose to use the `plot()` method or the command line, generating plots will provide you with a visual representation of your workflows, aiding in both development and presentation.
-
-## Next Steps
-
-If you're interested in exploring additional examples of flows, we have a variety of recommendations in our examples repository. Here are four specific flow examples, each showcasing unique use cases to help you match your current problem type to a specific example:
-
-1. **Email Auto Responder Flow**: This example demonstrates an infinite loop where a background job continually runs to automate email responses. It's a great use case for tasks that need to be performed repeatedly without manual intervention. [View Example](https://github.com/crewAIInc/crewAI-examples/tree/main/email_auto_responder_flow)
-
-2. **Lead Score Flow**: This flow showcases adding human-in-the-loop feedback and handling different conditional branches using the router. It's an excellent example of how to incorporate dynamic decision-making and human oversight into your workflows. [View Example](https://github.com/crewAIInc/crewAI-examples/tree/main/lead-score-flow)
-
-3. **Write a Book Flow**: This example excels at chaining multiple crews together, where the output of one crew is used by another. Specifically, one crew outlines an entire book, and another crew generates chapters based on the outline. Eventually, everything is connected to produce a complete book. This flow is perfect for complex, multi-step processes that require coordination between different tasks. [View Example](https://github.com/crewAIInc/crewAI-examples/tree/main/write_a_book_with_flows)
-
-4. **Meeting Assistant Flow**: This flow demonstrates how to broadcast one event to trigger multiple follow-up actions. For instance, after a meeting is completed, the flow can update a Trello board, send a Slack message, and save the results. It's a great example of handling multiple outcomes from a single event, making it ideal for comprehensive task management and notification systems. [View Example](https://github.com/crewAIInc/crewAI-examples/tree/main/meeting_assistant_flow)
-
-By exploring these examples, you can gain insights into how to leverage CrewAI Flows for various use cases, from automating repetitive tasks to managing complex, multi-step processes with dynamic decision-making and human feedback.
-
-Also, check out our YouTube video on how to use flows in CrewAI below!
-
-<iframe
-  className="w-full aspect-video rounded-xl"
-  src="https://www.youtube.com/embed/MTb5my6VOT8"
-  title="CrewAI Flows overview"
-  frameBorder="0"
-  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
-  referrerPolicy="strict-origin-when-cross-origin"
-  allowFullScreen
-></iframe>
+For visualization:
+- Use `flow.plot("my_flow_plot")` in code, or
+- Use `crewai flow plot` in CLI projects.
 
 ## Running Flows
 
@@ -946,7 +801,7 @@ There are two ways to run a flow:
 You can run a flow programmatically by creating an instance of your flow class and calling the `kickoff()` method:
 
 ```python
-flow = ExampleFlow()
+flow = SupportTriageFlow()
 result = flow.kickoff()
 ```
 
@@ -975,6 +830,79 @@ result = streaming.result
 
 Learn more about streaming in the [Streaming Flow Execution](/en/learn/streaming-flow-execution) guide.
 
+## Memory in Flows
+
+Every Flow automatically has access to CrewAI's unified [Memory](/concepts/memory) system. You can store, recall, and extract memories directly inside any flow method using three built-in convenience methods.
+
+### Built-in Methods
+
+| Method | Description |
+| :--- | :--- |
+| `self.remember(content, **kwargs)` | Store content in memory. Accepts optional `scope`, `categories`, `metadata`, `importance`. |
+| `self.recall(query, **kwargs)` | Retrieve relevant memories. Accepts optional `scope`, `categories`, `limit`, `depth`. |
+| `self.extract_memories(content)` | Break raw text into discrete, self-contained memory statements. |
+
+A default `Memory()` instance is created automatically when the Flow initializes. You can also pass a custom one:
+
+```python
+from crewai.flow.flow import Flow
+from crewai import Memory
+
+custom_memory = Memory(
+    recency_weight=0.5,
+    recency_half_life_days=7,
+    embedder={"provider": "ollama", "config": {"model_name": "mxbai-embed-large"}},
+)
+
+flow = MyFlow(memory=custom_memory)
+```
+
+### Example: Research and Analyze Flow
+
+```python
+from crewai.flow.flow import Flow, listen, start
+
+
+class ResearchAnalysisFlow(Flow):
+    @start()
+    def gather_data(self):
+        # Simulate research findings
+        findings = (
+            "PostgreSQL handles 10k concurrent connections with connection pooling. "
+            "MySQL caps at around 5k. MongoDB scales horizontally but adds complexity."
+        )
+
+        # Extract atomic facts and remember each one
+        memories = self.extract_memories(findings)
+        for mem in memories:
+            self.remember(mem, scope="/research/databases")
+
+        return findings
+
+    @listen(gather_data)
+    def analyze(self, raw_findings):
+        # Recall relevant past research (from this run or previous runs)
+        past = self.recall("database performance and scaling", limit=10, depth="shallow")
+
+        context_lines = [f"- {m.record.content}" for m in past]
+        context = "\n".join(context_lines) if context_lines else "No prior context."
+
+        return {
+            "new_findings": raw_findings,
+            "prior_context": context,
+            "total_memories": len(past),
+        }
+
+
+flow = ResearchAnalysisFlow()
+result = flow.kickoff()
+print(result)
+```
+
+Because memory persists across runs (backed by LanceDB on disk), the `analyze` step will recall findings from previous executions too -- enabling flows that learn and accumulate knowledge over time.
+
+See the [Memory documentation](/concepts/memory) for details on scopes, slices, composite scoring, embedder configuration, and more.
+
 ### Using the CLI
 
 Starting from version 0.103.0, you can run flows using the `crewai run` command:
@@ -992,3 +920,21 @@ crewai flow kickoff
 ```
 
 However, the `crewai run` command is now the preferred method as it works for both crews and flows.
+
+## Common Failure Modes
+
+### Router branch not firing
+- Cause: returned label does not match a `@listen("label")` value.
+- Fix: align router return strings with listener labels exactly.
+
+### State fields missing at runtime
+- Cause: untyped dynamic fields or missing kickoff inputs.
+- Fix: use typed state and validate required fields in `@start()`.
+
+### Prompt/token growth over time
+- Cause: appending unbounded message history in state.
+- Fix: apply sliding-window state and summary compaction patterns.
+
+### Non-idempotent retries
+- Cause: side effects executed on retried steps.
+- Fix: add idempotency keys/markers to state and guard external writes.

docs/en/concepts/planning.mdx

@@ -10,6 +10,17 @@ mode: "wide"
 The planning feature in CrewAI allows you to add planning capability to your crew. When enabled, before each Crew iteration, 
 all Crew information is sent to an AgentPlanner that will plan the tasks step by step, and this plan will be added to each task description.
 
+## When to Use Planning
+
+- Tasks require multi-step decomposition before execution.
+- You need more consistent execution quality on complex tasks.
+- You want transparent planning traces in crew runs.
+
+## When Not to Use Planning
+
+- Tasks are simple and deterministic.
+- Latency and token budget are strict and planning overhead is not justified.
+
 ### Using the Planning Feature
 
 Getting started with the planning feature is very easy, the only step required is to add `planning=True` to your Crew:
@@ -31,7 +42,7 @@ my_crew = Crew(
 From this point on, your crew will have planning enabled, and the tasks will be planned before each iteration.
 
 <Warning>
-When planning is enabled, crewAI will use `gpt-4o-mini` as the default LLM for planning, which requires a valid OpenAI API key. Since your agents might be using different LLMs, this could cause confusion if you don't have an OpenAI API key configured or if you're experiencing unexpected behavior related to LLM API calls.
+Planning model defaults can vary by version and environment. To avoid implicit provider dependencies, set `planning_llm` explicitly in your crew configuration.
 </Warning>
 
 #### Planning LLM
@@ -152,4 +163,14 @@ A list with 10 bullet points of the most relevant information about AI LLMs.
 **Expected Output:**
 A fully fledged report with the main topics, each with a full section of information. Formatted as markdown without '```'.
 ```
-</CodeGroup>
+</CodeGroup>
+
+## Common Failure Modes
+
+### Planning adds cost/latency without quality gains
+- Cause: planning enabled for simple tasks.
+- Fix: disable `planning` for straightforward pipelines.
+
+### Unexpected provider authentication errors
+- Cause: implicit planner model/provider assumptions.
+- Fix: set `planning_llm` explicitly and ensure matching credentials are configured.

docs/en/concepts/processes.mdx

@@ -12,11 +12,20 @@ mode: "wide"
   These processes ensure tasks are distributed and executed efficiently, in alignment with a predefined strategy.
 </Tip>
 
+## When to Use Each Process
+
+- Use `sequential` when task order is fixed and outputs feed directly into the next task.
+- Use `hierarchical` when you need a manager to delegate and validate work dynamically.
+
+## When Not to Use Hierarchical
+
+- You do not need dynamic delegation.
+- You cannot provide a reliable `manager_llm` or `manager_agent`.
+
 ## Process Implementations
 
 - **Sequential**: Executes tasks sequentially, ensuring tasks are completed in an orderly progression.
 - **Hierarchical**: Organizes tasks in a managerial hierarchy, where tasks are delegated and executed based on a structured chain of command. A manager language model (`manager_llm`) or a custom manager agent (`manager_agent`) must be specified in the crew to enable the hierarchical process, facilitating the creation and management of tasks by the manager.
-- **Consensual Process (Planned)**: Aiming for collaborative decision-making among agents on task execution, this process type introduces a democratic approach to task management within CrewAI. It is planned for future development and is not currently implemented in the codebase.
 
 ## The Role of Processes in Teamwork
 Processes enable individual agents to operate as a cohesive unit, streamlining their efforts to achieve common objectives with efficiency and coherence.
@@ -59,9 +68,17 @@ Emulates a corporate hierarchy, CrewAI allows specifying a custom manager agent
 
 ## Process Class: Detailed Overview
 
-The `Process` class is implemented as an enumeration (`Enum`), ensuring type safety and restricting process values to the defined types (`sequential`, `hierarchical`). The consensual process is planned for future inclusion, emphasizing our commitment to continuous development and innovation.
+The `Process` class is implemented as an enumeration (`Enum`), ensuring type safety and restricting process values to the defined types (`sequential`, `hierarchical`).
 
 ## Conclusion
 
 The structured collaboration facilitated by processes within CrewAI is crucial for enabling systematic teamwork among agents. 
-This documentation has been updated to reflect the latest features, enhancements, and the planned integration of the Consensual Process, ensuring users have access to the most current and comprehensive information.
+## Common Failure Modes
+
+### Hierarchical process fails at startup
+- Cause: missing `manager_llm` or `manager_agent`.
+- Fix: provide one of them explicitly in crew configuration.
+
+### Sequential process produces weak outputs
+- Cause: task boundaries/context are underspecified.
+- Fix: improve task descriptions, expected outputs, and task context chaining.

docs/en/concepts/tasks.mdx

@@ -46,7 +46,7 @@ crew = Crew(
 ## Task Attributes
 
 | Attribute                              | Parameters              | Type                        | Description                                                                                                     |
-| :------------------------------------- | :---------------------- | :-------------------------- | :-------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
+| :------------------------------------- | :---------------------- | :-------------------------- | :-------------------------------------------------------------------------------------------------------------- |
 | **Description**                        | `description`           | `str`                       | A clear, concise statement of what the task entails.                                                            |
 | **Expected Output**                    | `expected_output`       | `str`                       | A detailed description of what the task's completion looks like.                                                |
 | **Name** _(optional)_                  | `name`                  | `Optional[str]`             | A name identifier for the task.                                                                                 |
@@ -63,7 +63,7 @@ crew = Crew(
 | **Output Pydantic** _(optional)_       | `output_pydantic`       | `Optional[Type[BaseModel]]` | A Pydantic model for task output.                                                                               |
 | **Callback** _(optional)_              | `callback`              | `Optional[Any]`             | Function/object to be executed after task completion.                                                           |
 | **Guardrail** _(optional)_             | `guardrail`             | `Optional[Callable]`        | Function to validate task output before proceeding to next task.                                                |
-| **Guardrails** _(optional)_            | `guardrails`            | `Optional[List[Callable]    | List[str]]`                                                                                                     | List of guardrails to validate task output before proceeding to next task. |
+| **Guardrails** _(optional)_            | `guardrails`            | `Optional[List[Callable]]`  | List of guardrails to validate task output before proceeding to next task.                                      |
 | **Guardrail Max Retries** _(optional)_ | `guardrail_max_retries` | `Optional[int]`             | Maximum number of retries when guardrail validation fails. Defaults to 3.                                       |
 
 <Note type="warning" title="Deprecated: max_retries">

docs/en/concepts/testing.mdx

@@ -9,9 +9,20 @@ mode: "wide"
 
 Testing is a crucial part of the development process, and it is essential to ensure that your crew is performing as expected. With crewAI, you can easily test your crew and evaluate its performance using the built-in testing capabilities.
 
+## When to Use Testing
+
+- Before promoting a crew to production.
+- After changing prompts, tools, or model configurations.
+- When benchmarking quality/cost/latency tradeoffs.
+
+## When Not to Rely on Testing Alone
+
+- For safety-critical deployments without human review gates.
+- When test datasets are too small or unrepresentative.
+
 ### Using the Testing Feature
 
-We added the CLI command `crewai test` to make it easy to test your crew. This command will run your crew for a specified number of iterations and provide detailed performance metrics. The parameters are `n_iterations` and `model`, which are optional and default to 2 and `gpt-4o-mini` respectively. For now, the only provider available is OpenAI.
+Use the CLI command `crewai test` to run repeated crew executions and compare outputs across iterations. The parameters are `n_iterations` and `model`, which are optional and default to `2` and `gpt-4o-mini`.
 
 ```bash
 crewai test
@@ -47,3 +58,13 @@ A table of scores at the end will show the performance of the crew in terms of t
 | Execution Time (s) |  126  |  145  |    **135**     |                                |                                  |
 
 The example above shows the test results for two runs of the crew with two tasks, with the average total score for each task and the crew as a whole.
+
+## Common Failure Modes
+
+### Scores fluctuate too much between runs
+- Cause: high sampling randomness or unstable prompts.
+- Fix: lower temperature and tighten output constraints.
+
+### Good test scores but poor production quality
+- Cause: test prompts do not match real workload.
+- Fix: build a representative test set from real production inputs.

docs/en/concepts/tools.mdx

@@ -10,6 +10,17 @@ mode: "wide"
 CrewAI tools empower agents with capabilities ranging from web searching and data analysis to collaboration and delegating tasks among coworkers.
 This documentation outlines how to create, integrate, and leverage these tools within the CrewAI framework, including a new focus on collaboration tools.
 
+## When to Use Tools
+
+- Agents need external data or side effects.
+- You need deterministic actions wrapped in reusable interfaces.
+- You need to connect APIs, files, databases, or browser actions into agent workflows.
+
+## When Not to Use Tools
+
+- The task can be solved entirely from prompt context.
+- The external side effect cannot be made safe or idempotent.
+
 ## What is a Tool?
 
 A tool in CrewAI is a skill or function that agents can utilize to perform various actions.
@@ -285,3 +296,17 @@ writer1 = Agent(
 Tools are pivotal in extending the capabilities of CrewAI agents, enabling them to undertake a broad spectrum of tasks and collaborate effectively.
 When building solutions with CrewAI, leverage both custom and existing tools to empower your agents and enhance the AI ecosystem. Consider utilizing error handling,
 caching mechanisms, and the flexibility of tool arguments to optimize your agents' performance and capabilities.
+
+## Common Failure Modes
+
+### Tool schema mismatch
+- Cause: model-generated arguments do not match tool signature.
+- Fix: tighten tool descriptions and validate input schemas.
+
+### Repeated side effects
+- Cause: retries trigger duplicate writes/actions.
+- Fix: add idempotency keys and deduplication checks in tool logic.
+
+### Tool timeouts under load
+- Cause: unbounded retries or slow external services.
+- Fix: set explicit timeout/retry policy and graceful fallbacks.

docs/en/enterprise/features/flow-hitl-management.mdx

@@ -38,22 +38,21 @@ CrewAI Enterprise provides a comprehensive Human-in-the-Loop (HITL) management s
 Configure human review checkpoints within your Flows using the `@human_feedback` decorator. When execution reaches a review point, the system pauses, notifies the assignee via email, and waits for a response.
 
 ```python
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 
 class ContentApprovalFlow(Flow):
     @start()
     def generate_content(self):
-        # AI generates content
         return "Generated marketing copy for Q1 campaign..."
 
-    @listen(generate_content)
     @human_feedback(
         message="Please review this content for brand compliance:",
         emit=["approved", "rejected", "needs_revision"],
     )
-    def review_content(self, content):
-        return content
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "Marketing copy for review..."
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
@@ -62,10 +61,6 @@ class ContentApprovalFlow(Flow):
     @listen("rejected")
     def archive_content(self, result: HumanFeedbackResult):
         print(f"Content rejected. Reason: {result.feedback}")
-
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        print(f"Revision requested: {result.feedback}")
 ```
 
 For complete implementation details, see the [Human Feedback in Flows](/en/learn/human-feedback-in-flows) guide.

docs/en/enterprise/integrations/google_contacts.mdx

@@ -224,6 +224,60 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `groupFields` (string, optional): Fields to include (e.g., 'name,memberCount,clientData'). Default: name,memberCount
 
   </Accordion>
+
+  <Accordion title="google_contacts/get_contact_group">
+    **Description:** Get a specific contact group by resource name.
+
+    **Parameters:**
+    - `resourceName` (string, required): The resource name of the contact group (e.g., 'contactGroups/myContactGroup')
+    - `maxMembers` (integer, optional): Maximum number of members to include. Minimum: 0, Maximum: 20000
+    - `groupFields` (string, optional): Fields to include (e.g., 'name,memberCount,clientData'). Default: name,memberCount
+
+  </Accordion>
+
+  <Accordion title="google_contacts/create_contact_group">
+    **Description:** Create a new contact group (label).
+
+    **Parameters:**
+    - `name` (string, required): The name of the contact group
+    - `clientData` (array, optional): Client-specific data
+      ```json
+      [
+        {
+          "key": "data_key",
+          "value": "data_value"
+        }
+      ]
+      ```
+
+  </Accordion>
+
+  <Accordion title="google_contacts/update_contact_group">
+    **Description:** Update a contact group's information.
+
+    **Parameters:**
+    - `resourceName` (string, required): The resource name of the contact group (e.g., 'contactGroups/myContactGroup')
+    - `name` (string, required): The name of the contact group
+    - `clientData` (array, optional): Client-specific data
+      ```json
+      [
+        {
+          "key": "data_key",
+          "value": "data_value"
+        }
+      ]
+      ```
+
+  </Accordion>
+
+  <Accordion title="google_contacts/delete_contact_group">
+    **Description:** Delete a contact group.
+
+    **Parameters:**
+    - `resourceName` (string, required): The resource name of the contact group to delete (e.g., 'contactGroups/myContactGroup')
+    - `deleteContacts` (boolean, optional): Whether to delete contacts in the group as well. Default: false
+
+  </Accordion>
 </AccordionGroup>
 
 ## Usage Examples

docs/en/enterprise/integrations/google_docs.mdx

@@ -132,6 +132,297 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `endIndex` (integer, required): The end index of the range.
 
   </Accordion>
+
+  <Accordion title="google_docs/create_document_with_content">
+    **Description:** Create a new Google Document with content in one action.
+
+    **Parameters:**
+    - `title` (string, required): The title for the new document. Appears at the top of the document and in Google Drive.
+    - `content` (string, optional): The text content to insert into the document. Use `\n` for new paragraphs.
+
+  </Accordion>
+
+  <Accordion title="google_docs/append_text">
+    **Description:** Append text to the end of a Google Document. Automatically inserts at the document end without needing to specify an index.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID from create_document response or URL.
+    - `text` (string, required): Text to append at the end of the document. Use `\n` for new paragraphs.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_bold">
+    **Description:** Make text bold or remove bold formatting in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of text to format.
+    - `endIndex` (integer, required): End position of text to format (exclusive).
+    - `bold` (boolean, required): Set `true` to make bold, `false` to remove bold.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_italic">
+    **Description:** Make text italic or remove italic formatting in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of text to format.
+    - `endIndex` (integer, required): End position of text to format (exclusive).
+    - `italic` (boolean, required): Set `true` to make italic, `false` to remove italic.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_underline">
+    **Description:** Add or remove underline formatting from text in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of text to format.
+    - `endIndex` (integer, required): End position of text to format (exclusive).
+    - `underline` (boolean, required): Set `true` to underline, `false` to remove underline.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_strikethrough">
+    **Description:** Add or remove strikethrough formatting from text in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of text to format.
+    - `endIndex` (integer, required): End position of text to format (exclusive).
+    - `strikethrough` (boolean, required): Set `true` to add strikethrough, `false` to remove.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_font_size">
+    **Description:** Change the font size of text in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of text to format.
+    - `endIndex` (integer, required): End position of text to format (exclusive).
+    - `fontSize` (number, required): Font size in points. Common sizes: 10, 11, 12, 14, 16, 18, 24, 36.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_color">
+    **Description:** Change the color of text using RGB values (0-1 scale) in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of text to format.
+    - `endIndex` (integer, required): End position of text to format (exclusive).
+    - `red` (number, required): Red component (0-1). Example: `1` for full red.
+    - `green` (number, required): Green component (0-1). Example: `0.5` for half green.
+    - `blue` (number, required): Blue component (0-1). Example: `0` for no blue.
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_hyperlink">
+    **Description:** Turn existing text into a clickable hyperlink in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of text to make into a link.
+    - `endIndex` (integer, required): End position of text to make into a link (exclusive).
+    - `url` (string, required): The URL the link should point to. Example: `"https://example.com"`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/apply_heading_style">
+    **Description:** Apply a heading or paragraph style to a text range in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of paragraph(s) to style.
+    - `endIndex` (integer, required): End position of paragraph(s) to style.
+    - `style` (string, required): The style to apply. Enum: `NORMAL_TEXT`, `TITLE`, `SUBTITLE`, `HEADING_1`, `HEADING_2`, `HEADING_3`, `HEADING_4`, `HEADING_5`, `HEADING_6`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_paragraph_alignment">
+    **Description:** Set text alignment for paragraphs in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of paragraph(s) to align.
+    - `endIndex` (integer, required): End position of paragraph(s) to align.
+    - `alignment` (string, required): Text alignment. Enum: `START` (left), `CENTER`, `END` (right), `JUSTIFIED`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_line_spacing">
+    **Description:** Set line spacing for paragraphs in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of paragraph(s).
+    - `endIndex` (integer, required): End position of paragraph(s).
+    - `lineSpacing` (number, required): Line spacing as percentage. `100` = single, `115` = 1.15x, `150` = 1.5x, `200` = double.
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_paragraph_bullets">
+    **Description:** Convert paragraphs to a bulleted or numbered list in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of paragraphs to convert to list.
+    - `endIndex` (integer, required): End position of paragraphs to convert to list.
+    - `bulletPreset` (string, required): Bullet/numbering style. Enum: `BULLET_DISC_CIRCLE_SQUARE`, `BULLET_DIAMONDX_ARROW3D_SQUARE`, `BULLET_CHECKBOX`, `BULLET_ARROW_DIAMOND_DISC`, `BULLET_STAR_CIRCLE_SQUARE`, `NUMBERED_DECIMAL_ALPHA_ROMAN`, `NUMBERED_DECIMAL_ALPHA_ROMAN_PARENS`, `NUMBERED_DECIMAL_NESTED`, `NUMBERED_UPPERALPHA_ALPHA_ROMAN`, `NUMBERED_UPPERROMAN_UPPERALPHA_DECIMAL`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_paragraph_bullets">
+    **Description:** Remove bullets or numbering from paragraphs in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `startIndex` (integer, required): Start position of list paragraphs.
+    - `endIndex` (integer, required): End position of list paragraphs.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_table_with_content">
+    **Description:** Insert a table with content into a Google Document in one action. Provide content as a 2D array.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `rows` (integer, required): Number of rows in the table.
+    - `columns` (integer, required): Number of columns in the table.
+    - `index` (integer, optional): Position to insert the table. If not provided, the table is inserted at the end of the document.
+    - `content` (array, required): Table content as a 2D array. Each inner array is a row. Example: `[["Year", "Revenue"], ["2023", "$43B"], ["2024", "$45B"]]`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_table_row">
+    **Description:** Insert a new row above or below a reference cell in an existing table.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `tableStartIndex` (integer, required): The start index of the table. Get from get_document.
+    - `rowIndex` (integer, required): Row index (0-based) of reference cell.
+    - `columnIndex` (integer, optional): Column index (0-based) of reference cell. Default is `0`.
+    - `insertBelow` (boolean, optional): If `true`, insert below the reference row. If `false`, insert above. Default is `true`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_table_column">
+    **Description:** Insert a new column left or right of a reference cell in an existing table.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `tableStartIndex` (integer, required): The start index of the table.
+    - `rowIndex` (integer, optional): Row index (0-based) of reference cell. Default is `0`.
+    - `columnIndex` (integer, required): Column index (0-based) of reference cell.
+    - `insertRight` (boolean, optional): If `true`, insert to the right. If `false`, insert to the left. Default is `true`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_table_row">
+    **Description:** Delete a row from an existing table in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `tableStartIndex` (integer, required): The start index of the table.
+    - `rowIndex` (integer, required): Row index (0-based) to delete.
+    - `columnIndex` (integer, optional): Column index (0-based) of any cell in the row. Default is `0`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_table_column">
+    **Description:** Delete a column from an existing table in a Google Document.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `tableStartIndex` (integer, required): The start index of the table.
+    - `rowIndex` (integer, optional): Row index (0-based) of any cell in the column. Default is `0`.
+    - `columnIndex` (integer, required): Column index (0-based) to delete.
+
+  </Accordion>
+
+  <Accordion title="google_docs/merge_table_cells">
+    **Description:** Merge a range of table cells into a single cell. Content from all cells is preserved.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `tableStartIndex` (integer, required): The start index of the table.
+    - `rowIndex` (integer, required): Starting row index (0-based) for the merge.
+    - `columnIndex` (integer, required): Starting column index (0-based) for the merge.
+    - `rowSpan` (integer, required): Number of rows to merge.
+    - `columnSpan` (integer, required): Number of columns to merge.
+
+  </Accordion>
+
+  <Accordion title="google_docs/unmerge_table_cells">
+    **Description:** Unmerge previously merged table cells back into individual cells.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `tableStartIndex` (integer, required): The start index of the table.
+    - `rowIndex` (integer, required): Row index (0-based) of the merged cell.
+    - `columnIndex` (integer, required): Column index (0-based) of the merged cell.
+    - `rowSpan` (integer, required): Number of rows the merged cell spans.
+    - `columnSpan` (integer, required): Number of columns the merged cell spans.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_inline_image">
+    **Description:** Insert an image from a public URL into a Google Document. The image must be publicly accessible, under 50MB, and in PNG/JPEG/GIF format.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `uri` (string, required): Public URL of the image. Must be accessible without authentication.
+    - `index` (integer, optional): Position to insert the image. If not provided, the image is inserted at the end of the document. Default is `1`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_section_break">
+    **Description:** Insert a section break to create document sections with different formatting.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `index` (integer, required): Position to insert the section break.
+    - `sectionType` (string, required): The type of section break. Enum: `CONTINUOUS` (stays on same page), `NEXT_PAGE` (starts a new page).
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_header">
+    **Description:** Create a header for the document. Returns a headerId which can be used with insert_text to add header content.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `type` (string, optional): Header type. Enum: `DEFAULT`. Default is `DEFAULT`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_footer">
+    **Description:** Create a footer for the document. Returns a footerId which can be used with insert_text to add footer content.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `type` (string, optional): Footer type. Enum: `DEFAULT`. Default is `DEFAULT`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_header">
+    **Description:** Delete a header from the document. Use get_document to find the headerId.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `headerId` (string, required): The header ID to delete. Get from get_document response.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_footer">
+    **Description:** Delete a footer from the document. Use get_document to find the footerId.
+
+    **Parameters:**
+    - `documentId` (string, required): The document ID.
+    - `footerId` (string, required): The footer ID to delete. Get from get_document response.
+
+  </Accordion>
 </AccordionGroup>
 
 ## Usage Examples

docs/en/enterprise/integrations/google_slides.mdx

@@ -62,6 +62,22 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="google_slides/get_presentation_metadata">
+    **Description:** Get lightweight metadata about a presentation (title, slide count, slide IDs). Use this first before fetching full content.
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation to retrieve.
+
+  </Accordion>
+
+  <Accordion title="google_slides/get_presentation_text">
+    **Description:** Extract all text content from a presentation. Returns slide IDs and text from shapes and tables only (no formatting).
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+
+  </Accordion>
+
   <Accordion title="google_slides/get_presentation">
     **Description:** Retrieves a presentation by ID.
 
@@ -96,6 +112,15 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="google_slides/get_slide_text">
+    **Description:** Extract text content from a single slide. Returns only text from shapes and tables (no formatting or styling).
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `pageObjectId` (string, required): The ID of the slide/page to get text from.
+
+  </Accordion>
+
   <Accordion title="google_slides/get_page">
     **Description:** Retrieves a specific page by its ID.
 
@@ -114,6 +139,120 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="google_slides/create_slide">
+    **Description:** Add an additional blank slide to a presentation. New presentations already have one blank slide - check get_presentation_metadata first. For slides with title/body areas, use create_slide_with_layout instead.
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `insertionIndex` (integer, optional): Where to insert the slide (0-based). If omitted, adds at the end.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_slide_with_layout">
+    **Description:** Create a slide with a predefined layout containing placeholder areas for title, body, etc. This is better than create_slide for structured content. After creating, use get_page to find placeholder IDs, then insert text into them.
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `layout` (string, required): Layout type. One of: `BLANK`, `TITLE`, `TITLE_AND_BODY`, `TITLE_AND_TWO_COLUMNS`, `TITLE_ONLY`, `SECTION_HEADER`, `ONE_COLUMN_TEXT`, `MAIN_POINT`, `BIG_NUMBER`. TITLE_AND_BODY is best for title+description. TITLE for title-only slides. SECTION_HEADER for section dividers.
+    - `insertionIndex` (integer, optional): Where to insert (0-based). Omit to add at end.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_text_box">
+    **Description:** Create a text box on a slide with content. Use this for titles, descriptions, paragraphs - not tables. Optionally specify position (x, y) and size (width, height) in EMU units (914400 EMU = 1 inch).
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `slideId` (string, required): The ID of the slide to add the text box to.
+    - `text` (string, required): The text content for the text box.
+    - `x` (integer, optional): X position in EMU (914400 = 1 inch). Default: 914400 (1 inch from left).
+    - `y` (integer, optional): Y position in EMU (914400 = 1 inch). Default: 914400 (1 inch from top).
+    - `width` (integer, optional): Width in EMU. Default: 7315200 (~8 inches).
+    - `height` (integer, optional): Height in EMU. Default: 914400 (~1 inch).
+
+  </Accordion>
+
+  <Accordion title="google_slides/delete_slide">
+    **Description:** Remove a slide from the presentation. Use get_presentation first to find the slide ID.
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `slideId` (string, required): The object ID of the slide to delete. Get from get_presentation.
+
+  </Accordion>
+
+  <Accordion title="google_slides/duplicate_slide">
+    **Description:** Create a copy of an existing slide. The duplicate is inserted immediately after the original.
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `slideId` (string, required): The object ID of the slide to duplicate. Get from get_presentation.
+
+  </Accordion>
+
+  <Accordion title="google_slides/move_slides">
+    **Description:** Reorder slides by moving them to a new position. Slide IDs must be in their current presentation order (no duplicates).
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `slideIds` (array of strings, required): Array of slide IDs to move. Must be in current presentation order.
+    - `insertionIndex` (integer, required): Target position (0-based). 0 = beginning, slide count = end.
+
+  </Accordion>
+
+  <Accordion title="google_slides/insert_youtube_video">
+    **Description:** Embed a YouTube video on a slide. The video ID is the value after "v=" in YouTube URLs (e.g., for youtube.com/watch?v=abc123, use "abc123").
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `slideId` (string, required): The ID of the slide to add the video to. Get from get_presentation.
+    - `videoId` (string, required): The YouTube video ID (the value after v= in the URL).
+
+  </Accordion>
+
+  <Accordion title="google_slides/insert_drive_video">
+    **Description:** Embed a video from Google Drive on a slide. The file ID can be found in the Drive file URL.
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `slideId` (string, required): The ID of the slide to add the video to. Get from get_presentation.
+    - `fileId` (string, required): The Google Drive file ID of the video.
+
+  </Accordion>
+
+  <Accordion title="google_slides/set_slide_background_image">
+    **Description:** Set a background image for a slide. The image URL must be publicly accessible.
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `slideId` (string, required): The ID of the slide to set the background for. Get from get_presentation.
+    - `imageUrl` (string, required): Publicly accessible URL of the image to use as background.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_table">
+    **Description:** Create an empty table on a slide. To create a table with content, use create_table_with_content instead.
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `slideId` (string, required): The ID of the slide to add the table to. Get from get_presentation.
+    - `rows` (integer, required): Number of rows in the table.
+    - `columns` (integer, required): Number of columns in the table.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_table_with_content">
+    **Description:** Create a table with content in one action. Provide content as a 2D array where each inner array is a row. Example: [["Header1", "Header2"], ["Row1Col1", "Row1Col2"]].
+
+    **Parameters:**
+    - `presentationId` (string, required): The ID of the presentation.
+    - `slideId` (string, required): The ID of the slide to add the table to. Get from get_presentation.
+    - `rows` (integer, required): Number of rows in the table.
+    - `columns` (integer, required): Number of columns in the table.
+    - `content` (array, required): Table content as 2D array. Each inner array is a row. Example: [["Year", "Revenue"], ["2023", "$10M"]].
+
+  </Accordion>
+
   <Accordion title="google_slides/import_data_from_sheet">
     **Description:** Imports data from a Google Sheet into a presentation.
 

docs/en/enterprise/integrations/microsoft_excel.mdx

@@ -169,6 +169,16 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="microsoft_excel/get_table_data">
+    **Description:** Get data from a specific table in an Excel worksheet.
+
+    **Parameters:**
+    - `file_id` (string, required): The ID of the Excel file
+    - `worksheet_name` (string, required): Name of the worksheet
+    - `table_name` (string, required): Name of the table
+
+  </Accordion>
+
   <Accordion title="microsoft_excel/create_chart">
     **Description:** Create a chart in an Excel worksheet.
 
@@ -201,6 +211,15 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="microsoft_excel/get_used_range_metadata">
+    **Description:** Get the used range metadata (dimensions only, no data) of an Excel worksheet.
+
+    **Parameters:**
+    - `file_id` (string, required): The ID of the Excel file
+    - `worksheet_name` (string, required): Name of the worksheet
+
+  </Accordion>
+
   <Accordion title="microsoft_excel/list_charts">
     **Description:** Get all charts in an Excel worksheet.
 

docs/en/enterprise/integrations/microsoft_onedrive.mdx

@@ -151,6 +151,49 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `item_id` (string, required): The ID of the file.
 
   </Accordion>
+
+  <Accordion title="microsoft_onedrive/list_files_by_path">
+    **Description:** List files and folders in a specific OneDrive path.
+
+    **Parameters:**
+    - `folder_path` (string, required): The folder path (e.g., 'Documents/Reports').
+    - `top` (integer, optional): Number of items to retrieve (max 1000). Default is `50`.
+    - `orderby` (string, optional): Order by field (e.g., "name asc", "lastModifiedDateTime desc"). Default is "name asc".
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/get_recent_files">
+    **Description:** Get recently accessed files from OneDrive.
+
+    **Parameters:**
+    - `top` (integer, optional): Number of items to retrieve (max 200). Default is `25`.
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/get_shared_with_me">
+    **Description:** Get files and folders shared with the user.
+
+    **Parameters:**
+    - `top` (integer, optional): Number of items to retrieve (max 200). Default is `50`.
+    - `orderby` (string, optional): Order by field. Default is "name asc".
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/get_file_by_path">
+    **Description:** Get information about a specific file or folder by path.
+
+    **Parameters:**
+    - `file_path` (string, required): The file or folder path (e.g., 'Documents/report.docx').
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/download_file_by_path">
+    **Description:** Download a file from OneDrive by its path.
+
+    **Parameters:**
+    - `file_path` (string, required): The file path (e.g., 'Documents/report.docx').
+
+  </Accordion>
 </AccordionGroup>
 
 ## Usage Examples

docs/en/enterprise/integrations/microsoft_outlook.mdx

@@ -133,6 +133,74 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `companyName` (string, optional): Contact's company name.
 
   </Accordion>
+
+  <Accordion title="microsoft_outlook/get_message">
+    **Description:** Get a specific email message by ID.
+
+    **Parameters:**
+    - `message_id` (string, required): The unique identifier of the message. Obtain from get_messages action.
+    - `select` (string, optional): Comma-separated list of properties to return. Example: "id,subject,body,from,receivedDateTime". Default is "id,subject,body,from,toRecipients,receivedDateTime".
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/reply_to_email">
+    **Description:** Reply to an email message.
+
+    **Parameters:**
+    - `message_id` (string, required): The unique identifier of the message to reply to. Obtain from get_messages action.
+    - `comment` (string, required): The reply message content. Can be plain text or HTML. The original message will be quoted below this content.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/forward_email">
+    **Description:** Forward an email message.
+
+    **Parameters:**
+    - `message_id` (string, required): The unique identifier of the message to forward. Obtain from get_messages action.
+    - `to_recipients` (array, required): Array of recipient email addresses to forward to. Example: ["john@example.com", "jane@example.com"].
+    - `comment` (string, optional): Optional message to include above the forwarded content. Can be plain text or HTML.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/mark_message_read">
+    **Description:** Mark a message as read or unread.
+
+    **Parameters:**
+    - `message_id` (string, required): The unique identifier of the message. Obtain from get_messages action.
+    - `is_read` (boolean, required): Set to true to mark as read, false to mark as unread.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/delete_message">
+    **Description:** Delete an email message.
+
+    **Parameters:**
+    - `message_id` (string, required): The unique identifier of the message to delete. Obtain from get_messages action.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/update_event">
+    **Description:** Update an existing calendar event.
+
+    **Parameters:**
+    - `event_id` (string, required): The unique identifier of the event. Obtain from get_calendar_events action.
+    - `subject` (string, optional): New subject/title for the event.
+    - `start_time` (string, optional): New start time in ISO 8601 format (e.g., "2024-01-20T10:00:00"). REQUIRED: Must also provide start_timezone when using this field.
+    - `start_timezone` (string, optional): Timezone for start time. REQUIRED when updating start_time. Examples: "Pacific Standard Time", "Eastern Standard Time", "UTC".
+    - `end_time` (string, optional): New end time in ISO 8601 format. REQUIRED: Must also provide end_timezone when using this field.
+    - `end_timezone` (string, optional): Timezone for end time. REQUIRED when updating end_time. Examples: "Pacific Standard Time", "Eastern Standard Time", "UTC".
+    - `location` (string, optional): New location for the event.
+    - `body` (string, optional): New body/description for the event. Supports HTML formatting.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/delete_event">
+    **Description:** Delete a calendar event.
+
+    **Parameters:**
+    - `event_id` (string, required): The unique identifier of the event to delete. Obtain from get_calendar_events action.
+
+  </Accordion>
 </AccordionGroup>
 
 ## Usage Examples

docs/en/enterprise/integrations/microsoft_sharepoint.mdx

@@ -78,6 +78,17 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="microsoft_sharepoint/get_drives">
+    **Description:** List all document libraries (drives) in a SharePoint site. Use this to discover available libraries before using file operations.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `top` (integer, optional): Maximum number of drives to return per page (1-999). Default is 100
+    - `skip_token` (string, optional): Pagination token from a previous response to fetch the next page of results
+    - `select` (string, optional): Comma-separated list of properties to return (e.g., 'id,name,webUrl,driveType')
+
+  </Accordion>
+
   <Accordion title="microsoft_sharepoint/get_site_lists">
     **Description:** Get all lists in a SharePoint site.
 
@@ -159,20 +170,317 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
-  <Accordion title="microsoft_sharepoint/get_drive_items">
-    **Description:** Get files and folders from a SharePoint document library.
+  <Accordion title="microsoft_sharepoint/list_files">
+    **Description:** Retrieve files and folders from a SharePoint document library. By default lists the root folder, but you can navigate into subfolders by providing a folder_id.
 
     **Parameters:**
-    - `site_id` (string, required): The ID of the SharePoint site
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `folder_id` (string, optional): The ID of the folder to list contents from. Use 'root' for the root folder, or provide a folder ID from a previous list_files call. Default is 'root'
+    - `top` (integer, optional): Maximum number of items to return per page (1-1000). Default is 50
+    - `skip_token` (string, optional): Pagination token from a previous response to fetch the next page of results
+    - `orderby` (string, optional): Sort order for results (e.g., 'name asc', 'size desc', 'lastModifiedDateTime desc'). Default is 'name asc'
+    - `filter` (string, optional): OData filter to narrow results (e.g., 'file ne null' for files only, 'folder ne null' for folders only)
+    - `select` (string, optional): Comma-separated list of fields to return (e.g., 'id,name,size,folder,file,webUrl,lastModifiedDateTime')
 
   </Accordion>
 
-  <Accordion title="microsoft_sharepoint/delete_drive_item">
-    **Description:** Delete a file or folder from SharePoint document library.
+  <Accordion title="microsoft_sharepoint/delete_file">
+    **Description:** Delete a file or folder from a SharePoint document library. For folders, all contents are deleted recursively. Items are moved to the site recycle bin.
 
     **Parameters:**
-    - `site_id` (string, required): The ID of the SharePoint site
-    - `item_id` (string, required): The ID of the file or folder to delete
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the file or folder to delete. Obtain from list_files
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/list_files_by_path">
+    **Description:** List files and folders in a SharePoint document library folder by its path. More efficient than multiple list_files calls for deep navigation.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `folder_path` (string, required): The full path to the folder without leading/trailing slashes (e.g., 'Documents', 'Reports/2024/Q1')
+    - `top` (integer, optional): Maximum number of items to return per page (1-1000). Default is 50
+    - `skip_token` (string, optional): Pagination token from a previous response to fetch the next page of results
+    - `orderby` (string, optional): Sort order for results (e.g., 'name asc', 'size desc'). Default is 'name asc'
+    - `select` (string, optional): Comma-separated list of fields to return (e.g., 'id,name,size,folder,file,webUrl,lastModifiedDateTime')
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/download_file">
+    **Description:** Download raw file content from a SharePoint document library. Use only for plain text files (.txt, .csv, .json). For Excel files, use the Excel-specific actions. For Word files, use get_word_document_content.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the file to download. Obtain from list_files or list_files_by_path
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_file_info">
+    **Description:** Retrieve detailed metadata for a specific file or folder in a SharePoint document library, including name, size, created/modified dates, and author information.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the file or folder. Obtain from list_files or list_files_by_path
+    - `select` (string, optional): Comma-separated list of properties to return (e.g., 'id,name,size,createdDateTime,lastModifiedDateTime,webUrl,createdBy,lastModifiedBy')
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/create_folder">
+    **Description:** Create a new folder in a SharePoint document library. By default creates the folder in the root; use parent_id to create subfolders.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `folder_name` (string, required): Name for the new folder. Cannot contain: \ / : * ? " < > |
+    - `parent_id` (string, optional): The ID of the parent folder. Use 'root' for the document library root, or provide a folder ID from list_files. Default is 'root'
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/search_files">
+    **Description:** Search for files and folders in a SharePoint document library by keywords. Searches file names, folder names, and file contents for Office documents. Do not use wildcards or special characters.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `query` (string, required): Search keywords (e.g., 'report', 'budget 2024'). Wildcards like *.txt are not supported
+    - `top` (integer, optional): Maximum number of results to return per page (1-1000). Default is 50
+    - `skip_token` (string, optional): Pagination token from a previous response to fetch the next page of results
+    - `select` (string, optional): Comma-separated list of fields to return (e.g., 'id,name,size,folder,file,webUrl,lastModifiedDateTime')
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/copy_file">
+    **Description:** Copy a file or folder to a new location within SharePoint. The original item remains unchanged. The copy operation is asynchronous for large files.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the file or folder to copy. Obtain from list_files or search_files
+    - `destination_folder_id` (string, required): The ID of the destination folder. Use 'root' for the root folder, or a folder ID from list_files
+    - `new_name` (string, optional): New name for the copy. If not provided, the original name is used
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/move_file">
+    **Description:** Move a file or folder to a new location within SharePoint. The item is removed from its original location. For folders, all contents are moved as well.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the file or folder to move. Obtain from list_files or search_files
+    - `destination_folder_id` (string, required): The ID of the destination folder. Use 'root' for the root folder, or a folder ID from list_files
+    - `new_name` (string, optional): New name for the moved item. If not provided, the original name is kept
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_worksheets">
+    **Description:** List all worksheets (tabs) in an Excel workbook stored in a SharePoint document library. Use the returned worksheet name with other Excel actions.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `select` (string, optional): Comma-separated list of properties to return (e.g., 'id,name,position,visibility')
+    - `filter` (string, optional): OData filter expression (e.g., "visibility eq 'Visible'" to exclude hidden sheets)
+    - `top` (integer, optional): Maximum number of worksheets to return. Minimum: 1, Maximum: 999
+    - `orderby` (string, optional): Sort order (e.g., 'position asc' to return sheets in tab order)
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/create_excel_worksheet">
+    **Description:** Create a new worksheet (tab) in an Excel workbook stored in a SharePoint document library. The new sheet is added at the end of the tab list.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `name` (string, required): Name for the new worksheet. Maximum 31 characters. Cannot contain: \ / * ? : [ ]. Must be unique within the workbook
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_range_data">
+    **Description:** Retrieve cell values from a specific range in an Excel worksheet stored in SharePoint. For reading all data without knowing dimensions, use get_excel_used_range instead.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet (tab) to read from. Obtain from get_excel_worksheets. Case-sensitive
+    - `range` (string, required): Cell range in A1 notation (e.g., 'A1:C10', 'A:C', '1:5', 'A1')
+    - `select` (string, optional): Comma-separated list of properties to return (e.g., 'address,values,formulas,numberFormat,text')
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/update_excel_range_data">
+    **Description:** Write values to a specific range in an Excel worksheet stored in SharePoint. Overwrites existing cell contents. The values array dimensions must match the range dimensions exactly.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet (tab) to update. Obtain from get_excel_worksheets. Case-sensitive
+    - `range` (string, required): Cell range in A1 notation where values will be written (e.g., 'A1:C3' for a 3x3 block)
+    - `values` (array, required): 2D array of values (rows containing cells). Example for A1:B2: [["Header1", "Header2"], ["Value1", "Value2"]]. Use null to clear a cell
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_used_range_metadata">
+    **Description:** Return only the metadata (address and dimensions) of the used range in a worksheet, without the actual cell values. Ideal for large files to understand spreadsheet size before reading data in chunks.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet (tab) to read. Obtain from get_excel_worksheets. Case-sensitive
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_used_range">
+    **Description:** Retrieve all cells containing data in a worksheet stored in SharePoint. Do not use for files larger than 2MB. For large files, use get_excel_used_range_metadata first, then get_excel_range_data to read in smaller chunks.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet (tab) to read. Obtain from get_excel_worksheets. Case-sensitive
+    - `select` (string, optional): Comma-separated list of properties to return (e.g., 'address,values,formulas,numberFormat,text,rowCount,columnCount')
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_cell">
+    **Description:** Retrieve the value of a single cell by row and column index from an Excel file in SharePoint. Indices are 0-based (row 0 = Excel row 1, column 0 = column A).
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet (tab). Obtain from get_excel_worksheets. Case-sensitive
+    - `row` (integer, required): 0-based row index (row 0 = Excel row 1). Valid range: 0-1048575
+    - `column` (integer, required): 0-based column index (column 0 = A, column 1 = B). Valid range: 0-16383
+    - `select` (string, optional): Comma-separated list of properties to return (e.g., 'address,values,formulas,numberFormat,text')
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/add_excel_table">
+    **Description:** Convert a cell range into a formatted Excel table with filtering, sorting, and structured data capabilities. Tables enable add_excel_table_row for appending data.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet containing the data range. Obtain from get_excel_worksheets
+    - `range` (string, required): Cell range to convert into a table, including headers and data (e.g., 'A1:D10' where A1:D1 contains column headers)
+    - `has_headers` (boolean, optional): Set to true if the first row contains column headers. Default is true
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_tables">
+    **Description:** List all tables in a specific Excel worksheet stored in SharePoint. Returns table properties including id, name, showHeaders, and showTotals.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet to get tables from. Obtain from get_excel_worksheets
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/add_excel_table_row">
+    **Description:** Append a new row to the end of an Excel table in a SharePoint file. The values array must have the same number of elements as the table has columns.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet containing the table. Obtain from get_excel_worksheets
+    - `table_name` (string, required): Name of the table to add the row to (e.g., 'Table1'). Obtain from get_excel_tables. Case-sensitive
+    - `values` (array, required): Array of cell values for the new row, one per column in table order (e.g., ["John Doe", "john@example.com", 25])
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_table_data">
+    **Description:** Get all rows from an Excel table in a SharePoint file as a data range. Easier than get_excel_range_data when working with structured tables since you don't need to know the exact range.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet containing the table. Obtain from get_excel_worksheets
+    - `table_name` (string, required): Name of the table to get data from (e.g., 'Table1'). Obtain from get_excel_tables. Case-sensitive
+    - `select` (string, optional): Comma-separated list of properties to return (e.g., 'address,values,formulas,numberFormat,text')
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/create_excel_chart">
+    **Description:** Create a chart visualization in an Excel worksheet stored in SharePoint from a data range. The chart is embedded in the worksheet.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet where the chart will be created. Obtain from get_excel_worksheets
+    - `chart_type` (string, required): Chart type (e.g., 'ColumnClustered', 'ColumnStacked', 'Line', 'LineMarkers', 'Pie', 'Bar', 'BarClustered', 'Area', 'Scatter', 'Doughnut')
+    - `source_data` (string, required): Data range for the chart in A1 notation, including headers (e.g., 'A1:B10')
+    - `series_by` (string, optional): How data series are organized: 'Auto', 'Columns', or 'Rows'. Default is 'Auto'
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/list_excel_charts">
+    **Description:** List all charts embedded in an Excel worksheet stored in SharePoint. Returns chart properties including id, name, chartType, height, width, and position.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet to list charts from. Obtain from get_excel_worksheets
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/delete_excel_worksheet">
+    **Description:** Permanently remove a worksheet (tab) and all its contents from an Excel workbook stored in SharePoint. Cannot be undone. A workbook must have at least one worksheet.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet to delete. Case-sensitive. All data, tables, and charts on this sheet will be permanently removed
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/delete_excel_table">
+    **Description:** Remove a table from an Excel worksheet in SharePoint. This deletes the table structure (filtering, formatting, table features) but preserves the underlying cell data.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+    - `worksheet_name` (string, required): Name of the worksheet containing the table. Obtain from get_excel_worksheets
+    - `table_name` (string, required): Name of the table to delete (e.g., 'Table1'). Obtain from get_excel_tables. The data in the cells will remain after table deletion
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/list_excel_names">
+    **Description:** Retrieve all named ranges defined in an Excel workbook stored in SharePoint. Named ranges are user-defined labels for cell ranges (e.g., 'SalesData' for A1:D100).
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Excel file in SharePoint. Obtain from list_files or search_files
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_word_document_content">
+    **Description:** Download and extract text content from a Word document (.docx) stored in a SharePoint document library. This is the recommended way to read Word documents from SharePoint.
+
+    **Parameters:**
+    - `site_id` (string, required): The full SharePoint site identifier from get_sites
+    - `drive_id` (string, required): The ID of the document library. Call get_drives first to get valid drive IDs
+    - `item_id` (string, required): The unique identifier of the Word document (.docx) in SharePoint. Obtain from list_files or search_files
 
   </Accordion>
 </AccordionGroup>

docs/en/enterprise/integrations/microsoft_teams.mdx

@@ -108,6 +108,86 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `join_web_url` (string, required): The join web URL of the meeting to search for.
 
   </Accordion>
+
+  <Accordion title="microsoft_teams/search_online_meetings_by_meeting_id">
+    **Description:** Search online meetings by external Meeting ID.
+
+    **Parameters:**
+    - `join_meeting_id` (string, required): The meeting ID (numeric code) that attendees use to join. This is the joinMeetingId shown in meeting invitations, not the Graph API meeting id.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/get_meeting">
+    **Description:** Get details of a specific online meeting.
+
+    **Parameters:**
+    - `meeting_id` (string, required): The Graph API meeting ID (a long alphanumeric string). Obtain from create_meeting or search_online_meetings actions. Different from the numeric joinMeetingId.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/get_team_members">
+    **Description:** Get members of a specific team.
+
+    **Parameters:**
+    - `team_id` (string, required): The unique identifier of the team. Obtain from get_teams action.
+    - `top` (integer, optional): Maximum number of members to retrieve per page (1-999). Default is `100`.
+    - `skip_token` (string, optional): Pagination token from a previous response. When the response includes @odata.nextLink, extract the $skiptoken parameter value and pass it here to get the next page of results.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/create_channel">
+    **Description:** Create a new channel in a team.
+
+    **Parameters:**
+    - `team_id` (string, required): The unique identifier of the team. Obtain from get_teams action.
+    - `display_name` (string, required): Name of the channel as displayed in Teams. Must be unique within the team. Max 50 characters.
+    - `description` (string, optional): Optional description explaining the channel's purpose. Visible in channel details. Max 1024 characters.
+    - `membership_type` (string, optional): Channel visibility. Enum: `standard`, `private`. "standard" = visible to all team members, "private" = visible only to specifically added members. Default is `standard`.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/get_message_replies">
+    **Description:** Get replies to a specific message in a channel.
+
+    **Parameters:**
+    - `team_id` (string, required): The unique identifier of the team. Obtain from get_teams action.
+    - `channel_id` (string, required): The unique identifier of the channel. Obtain from get_channels action.
+    - `message_id` (string, required): The unique identifier of the parent message. Obtain from get_messages action.
+    - `top` (integer, optional): Maximum number of replies to retrieve per page (1-50). Default is `50`.
+    - `skip_token` (string, optional): Pagination token from a previous response. When the response includes @odata.nextLink, extract the $skiptoken parameter value and pass it here to get the next page of results.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/reply_to_message">
+    **Description:** Reply to a message in a Teams channel.
+
+    **Parameters:**
+    - `team_id` (string, required): The unique identifier of the team. Obtain from get_teams action.
+    - `channel_id` (string, required): The unique identifier of the channel. Obtain from get_channels action.
+    - `message_id` (string, required): The unique identifier of the message to reply to. Obtain from get_messages action.
+    - `message` (string, required): The reply content. For HTML, include formatting tags. For text, plain text only.
+    - `content_type` (string, optional): Content format. Enum: `html`, `text`. "text" for plain text, "html" for rich text with formatting. Default is `text`.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/update_meeting">
+    **Description:** Update an existing online meeting.
+
+    **Parameters:**
+    - `meeting_id` (string, required): The unique identifier of the meeting. Obtain from create_meeting or search_online_meetings actions.
+    - `subject` (string, optional): New meeting title.
+    - `startDateTime` (string, optional): New start time in ISO 8601 format with timezone. Example: "2024-01-20T10:00:00-08:00".
+    - `endDateTime` (string, optional): New end time in ISO 8601 format with timezone.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/delete_meeting">
+    **Description:** Delete an online meeting.
+
+    **Parameters:**
+    - `meeting_id` (string, required): The unique identifier of the meeting to delete. Obtain from create_meeting or search_online_meetings actions.
+
+  </Accordion>
 </AccordionGroup>
 
 ## Usage Examples

docs/en/enterprise/integrations/microsoft_word.mdx

@@ -98,6 +98,26 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `file_id` (string, required): The ID of the document to delete.
 
   </Accordion>
+
+  <Accordion title="microsoft_word/copy_document">
+    **Description:** Copy a document to a new location in OneDrive.
+
+    **Parameters:**
+    - `file_id` (string, required): The ID of the document to copy
+    - `name` (string, optional): New name for the copied document
+    - `parent_id` (string, optional): The ID of the destination folder (defaults to root)
+
+  </Accordion>
+
+  <Accordion title="microsoft_word/move_document">
+    **Description:** Move a document to a new location in OneDrive.
+
+    **Parameters:**
+    - `file_id` (string, required): The ID of the document to move
+    - `parent_id` (string, required): The ID of the destination folder
+    - `name` (string, optional): New name for the moved document
+
+  </Accordion>
 </AccordionGroup>
 
 ## Usage Examples

docs/en/examples/cookbooks.mdx

@@ -8,6 +8,10 @@ mode: "wide"
 ## Quickstarts & Demos
 
 <CardGroup cols={3}>
+  <Card title="Flowstate Chat History" icon="comments" href="/en/learn/flowstate-chat-history">
+    Manage chat sessions with sliding-window history, summary compaction, and persisted Flow state.
+  </Card>
+
   <Card title="Collaboration" icon="people-arrows" href="https://github.com/crewAIInc/crewAI-quickstarts/blob/main/Collaboration/crewai_collaboration.ipynb">
     Coordinate multiple agents on shared tasks. Includes notebook with end-to-end collaboration pattern.
   </Card>

docs/en/examples/example.mdx

@@ -34,6 +34,10 @@ mode: "wide"
 ## Flows
 
 <CardGroup cols={3}>
+  <Card title="Flowstate Chat History" icon="comments" href="/en/learn/flowstate-chat-history">
+    Stateful chat pattern with compacted context and persisted session state.
+  </Card>
+
   <Card title="Content Creator Flow" icon="pen" href="https://github.com/crewAIInc/crewAI-examples/tree/main/flows/content_creator_flow">
     Multi‑crew content generation with routing.
   </Card>

docs/en/guides/coding-tools/agents-md.mdx

@@ -0,0 +1,61 @@
+---
+title: Coding Tools
+description: Use AGENTS.md to guide coding agents and IDEs across your CrewAI projects.
+icon: terminal
+mode: "wide"
+---
+
+## Why AGENTS.md
+
+`AGENTS.md` is a lightweight, repo-local instruction file that gives coding agents consistent, project-specific guidance. Keep it in the project root and treat it as the source of truth for how you want assistants to work: conventions, commands, architecture notes, and guardrails.
+
+## Create a Project with the CLI
+
+Use the CrewAI CLI to scaffold a project, then `AGENTS.md` will be automatically added at the root.
+
+```bash
+# Crew
+crewai create crew my_crew
+
+# Flow
+crewai create flow my_flow
+
+# Tool repository
+crewai tool create my_tool
+```
+
+## Tool Setup: Point Assistants to AGENTS.md
+
+### Codex
+
+Codex can be guided by `AGENTS.md` files placed in your repository. Use them to supply persistent project context such as conventions, commands, and workflow expectations.
+
+### Claude Code
+
+Claude Code stores project memory in `CLAUDE.md`. You can bootstrap it with `/init` and edit it using `/memory`. Claude Code also supports imports inside `CLAUDE.md`, so you can add a single line like `@AGENTS.md` to pull in the shared instructions without duplicating them.
+
+You can simply use:
+
+```bash
+mv AGENTS.md CLAUDE.md
+```
+
+### Gemini CLI and Google Antigravity
+
+Gemini CLI and Antigravity load a project context file (default: `GEMINI.md`) from the repo root and parent directories. You can configure it to read `AGENTS.md` instead (or in addition) by setting `context.fileName` in your Gemini CLI settings. For example, set it to `AGENTS.md` only, or include both `AGENTS.md` and `GEMINI.md` if you want to keep each tool’s format.
+
+You can simply use:
+
+```bash
+mv AGENTS.md GEMINI.md
+```
+
+### Cursor
+
+Cursor supports `AGENTS.md` as a project instruction file. Place it at the project root to provide guidance for Cursor’s coding assistant.
+
+### Windsurf
+
+Claude Code provides an official integration with Windsurf. If you use Claude Code inside Windsurf, follow the Claude Code guidance above and import `AGENTS.md` from `CLAUDE.md`.
+
+If you are using Windsurf’s native assistant, configure its project rules or instructions feature (if available) to read from `AGENTS.md` or paste the contents directly.

docs/en/guides/flows/mastering-flow-state.mdx

@@ -47,6 +47,23 @@ CrewAI offers two ways to manage state in your flows:
 
 Let's examine each approach in detail.
 
+### Flow State vs Memory: When to use each
+
+Both features keep context, but they solve different problems.
+
+| Dimension | Flow State (`self.state`) | Memory (`self.remember` / `self.recall`) |
+|---|---|---|
+| Primary purpose | Track execution and deterministic workflow data | Store and retrieve semantic knowledge across interactions |
+| Data shape | Explicit fields (dict/Pydantic model) | Text records with inferred scopes and ranked recall |
+| Typical lifetime | Current flow run (or persisted checkpoints) | Long-term knowledge over many runs |
+| Access pattern | Direct reads/writes (`self.state.field`) | Query-based retrieval (`self.recall("...")`) |
+| Best for | Routing flags, counters, intermediate outputs, chat window | Durable facts, prior outcomes, reusable context |
+| Chat use | Recent turns + running summary + control flags | Long-tail memory outside context window |
+
+Practical rule:
+- Use **state** for what your control flow depends on right now.
+- Use **memory** for what you may want to retrieve later by meaning.
+
 ## Unstructured State Management
 
 Unstructured state uses a dictionary-like approach, offering flexibility and simplicity for straightforward applications.

docs/en/index.mdx

@@ -27,8 +27,11 @@ mode: "wide"
   </div>
 
   <div style={{ display: 'flex', flexWrap: 'wrap', gap: 12, justifyContent: 'center' }}>
-    <a className="button button-primary" href="/en/quickstart">Get started</a>
-    <a className="button" href="/en/changelog">View changelog</a>
+    <a className="button button-primary" href="/en/installation">Install</a>
+    <a className="button" href="/en/quickstart">Quickstart</a>
+    <a className="button" href="/en/guides/crews/first-crew">First Crew</a>
+    <a className="button" href="/en/guides/flows/first-flow">First Flow</a>
+    <a className="button" href="/en/concepts/llms">LLM Setup</a>
     <a className="button" href="/en/api-reference/introduction">API Reference</a>
   </div>
 
@@ -36,17 +39,49 @@ mode: "wide"
 
 <div style={{ marginTop: 32 }} />
 
-## Get started
+## Start in 3 steps
 
 <CardGroup cols={3}>
-  <Card title="Introduction" href="/en/introduction" icon="sparkles">
-    Overview of CrewAI concepts, architecture, and what you can build with agents, crews, and flows.
-  </Card>
-  <Card title="Installation" href="/en/installation" icon="wrench">
+  <Card title="1) Install" href="/en/installation" icon="wrench">
     Install via `uv`, configure API keys, and set up the CLI for local development.
   </Card>
-  <Card title="Quickstart" href="/en/quickstart" icon="rocket">
-    Spin up your first crew in minutes. Learn the core runtime, project layout, and dev loop.
+  <Card title="2) Run Quickstart" href="/en/quickstart" icon="rocket">
+    Launch your first working crew with a minimal project and iterate from there.
+  </Card>
+  <Card title="3) Pick a path" href="/en/ai/overview" icon="sitemap">
+    Continue with canonical domain packs for Flows, Agents, Crews, LLMs, Memory, and Tools.
+  </Card>
+</CardGroup>
+
+## Most-used pages
+
+<CardGroup cols={3}>
+  <Card title="First Crew" href="/en/guides/crews/first-crew" icon="users">
+    Build a production-style crew with role/task configuration and execution flow.
+  </Card>
+  <Card title="First Flow" href="/en/guides/flows/first-flow" icon="arrow-progress">
+    Build event-driven orchestration with state, listeners, and routing.
+  </Card>
+  <Card title="Flowstate Chat History" href="/en/learn/flowstate-chat-history" icon="comments">
+    Stateful chat history pattern with persistence and summary compaction.
+  </Card>
+  <Card title="Agents" href="/en/concepts/agents" icon="user">
+    Agent role design, tool boundaries, and output contracts.
+  </Card>
+  <Card title="Crews" href="/en/concepts/crews" icon="users-gear">
+    Multi-agent collaboration patterns and process semantics.
+  </Card>
+  <Card title="Flows" href="/en/concepts/flows" icon="code-branch">
+    Deterministic orchestration, state lifecycle, persistence, and resume.
+  </Card>
+  <Card title="LLMs" href="/en/concepts/llms" icon="microchip-ai">
+    Model setup, provider config, routing patterns, and reliability defaults.
+  </Card>
+  <Card title="Memory" href="/en/concepts/memory" icon="database">
+    Semantic recall, scope strategy, and state-vs-memory architecture.
+  </Card>
+  <Card title="Tools" href="/en/tools/overview" icon="wrench">
+    Tool categories, integration surfaces, and practical usage patterns.
   </Card>
 </CardGroup>
 
@@ -90,7 +125,11 @@ mode: "wide"
 </CardGroup>
 
 <Callout title="Explore real-world patterns" icon="github">
-  Browse the <a href="/en/examples/cookbooks">examples and cookbooks</a> for end-to-end reference implementations across agents, flows, and enterprise automations.
+  Browse the <a href="/en/examples/cookbooks">examples and cookbooks</a> for end-to-end reference implementations across agents, flows, and enterprise automations. For a practical conversational pattern, start with <a href="/en/learn/flowstate-chat-history">Flowstate Chat History</a>.
+</Callout>
+
+<Callout title="AI-First Docs" icon="sitemap">
+  Use the <a href="/en/ai/overview">AI-First Documentation map</a> for canonical domain packs across Flows, Agents, Crews, LLMs, Memory, and Tools.
 </Callout>
 
 ## Stay connected

docs/en/introduction.mdx

@@ -16,6 +16,52 @@ It empowers developers to build production-ready multi-agent systems by combinin
 
 With over 100,000 developers certified through our community courses, CrewAI is the standard for enterprise-ready AI automation.
 
+## Start Here
+
+<CardGroup cols={3}>
+  <Card title="Install" href="/en/installation" icon="wrench">
+    Set up CrewAI, configure API keys, and prepare your local environment.
+  </Card>
+  <Card title="Quickstart" href="/en/quickstart" icon="rocket">
+    Run your first working crew with a minimal setup.
+  </Card>
+  <Card title="First Crew" href="/en/guides/crews/first-crew" icon="users-gear">
+    Build a production-style crew with roles, tasks, and execution flow.
+  </Card>
+  <Card title="First Flow" href="/en/guides/flows/first-flow" icon="arrow-progress">
+    Build event-driven orchestration with state, listeners, and routers.
+  </Card>
+  <Card title="LLM Setup" href="/en/concepts/llms" icon="microchip-ai">
+    Configure providers, models, and reliability defaults.
+  </Card>
+  <Card title="API Reference" href="/en/api-reference/introduction" icon="book">
+    Use kickoff, resume, and status endpoints for production integrations.
+  </Card>
+</CardGroup>
+
+## Most-used Docs
+
+<CardGroup cols={3}>
+  <Card title="Agents" href="/en/concepts/agents" icon="user">
+    Role design, tool boundaries, and output contracts.
+  </Card>
+  <Card title="Crews" href="/en/concepts/crews" icon="users">
+    Multi-agent coordination and process choices.
+  </Card>
+  <Card title="Flows" href="/en/concepts/flows" icon="code-branch">
+    Deterministic orchestration, state, persistence, and resume.
+  </Card>
+  <Card title="Memory" href="/en/concepts/memory" icon="database">
+    Scope strategy and semantic recall across runs.
+  </Card>
+  <Card title="Flowstate Chat History" href="/en/learn/flowstate-chat-history" icon="comments">
+    Stateful chat context with summary compaction and persistence.
+  </Card>
+  <Card title="AI-First Docs Map" href="/en/ai/overview" icon="sitemap">
+    Canonical domain packs for Flows, Agents, Crews, LLMs, Memory, and Tools.
+  </Card>
+</CardGroup>
+
 ## The CrewAI Architecture
 
 CrewAI's architecture is designed to balance autonomy with control.
@@ -130,7 +176,7 @@ For any production-ready application, **start with a Flow**.
   <Card
     title="Quick Start"
     icon="bolt"
-    href="en/quickstart"
+    href="/en/quickstart"
   >
     Follow our quickstart guide to create your first CrewAI agent and get hands-on experience.
   </Card>

docs/en/learn/flowstate-chat-history.mdx

@@ -0,0 +1,167 @@
+---
+title: "Flowstate Chat History"
+description: "Build a stateful chat workflow that keeps context compact, persistent, and production-friendly."
+icon: "comments"
+mode: "wide"
+---
+
+## Overview
+
+This guide shows a practical pattern for managing LLM chat history with Flow state:
+
+- Keep recent turns in a sliding window
+- Summarize older turns into a compact running summary
+- Persist state automatically with `@persist()`
+- Keep optional long-term recall using Flow memory
+
+## Why this pattern works
+
+Naively appending every message to prompts causes token bloat and unstable behavior over long sessions. A better approach is:
+
+1. Keep only the most recent turns in `state.messages`
+2. Move older turns into `state.running_summary`
+3. Build prompts from `running_summary + recent messages`
+
+## Prerequisites
+
+1. CrewAI installed and configured
+2. API key configured for your model provider
+3. Basic familiarity with Flow decorators (`@start`, `@listen`)
+
+## Step 1: Define typed chat state
+
+```python Code
+from typing import Dict, List
+from pydantic import BaseModel, Field
+
+
+class ChatSessionState(BaseModel):
+    session_id: str = "demo-session"
+    running_summary: str = ""
+    messages: List[Dict[str, str]] = Field(default_factory=list)
+    max_recent_messages: int = 8
+    last_user_message: str = ""
+    assistant_reply: str = ""
+    turn_count: int = 0
+```
+
+## Step 2: Build the Flow
+
+```python Code
+from crewai.flow.flow import Flow, start, listen
+from crewai.flow.persistence import persist
+from litellm import completion
+
+
+@persist()
+class ChatHistoryFlow(Flow[ChatSessionState]):
+    model = "gpt-4o-mini"
+
+    @start()
+    def capture_user_message(self):
+        self.state.last_user_message = self.state.last_user_message.strip()
+        self.state.messages.append(
+            {"role": "user", "content": self.state.last_user_message}
+        )
+        self.state.turn_count += 1
+        return self.state.last_user_message
+
+    @listen(capture_user_message)
+    def compact_old_history(self, _):
+        if len(self.state.messages) <= self.state.max_recent_messages:
+            return "no_compaction"
+
+        overflow = self.state.messages[:-self.state.max_recent_messages]
+        self.state.messages = self.state.messages[-self.state.max_recent_messages :]
+        overflow_text = "\n".join(
+            f"{m['role']}: {m['content']}" for m in overflow
+        )
+
+        summary_prompt = [
+            {
+                "role": "system",
+                "content": "Summarize old chat turns into short bullet points. Preserve facts, constraints, and decisions.",
+            },
+            {
+                "role": "user",
+                "content": (
+                    f"Existing summary:\n{self.state.running_summary or '(empty)'}\n\n"
+                    f"New old turns:\n{overflow_text}"
+                ),
+            },
+        ]
+        summary_response = completion(model=self.model, messages=summary_prompt)
+        self.state.running_summary = summary_response["choices"][0]["message"]["content"]
+        return "compacted"
+
+    @listen(compact_old_history)
+    def generate_reply(self, _):
+        system_context = (
+            "You are a helpful assistant.\n"
+            f"Conversation summary so far:\n{self.state.running_summary or '(none)'}"
+        )
+
+        response = completion(
+            model=self.model,
+            messages=[{"role": "system", "content": system_context}, *self.state.messages],
+        )
+        answer = response["choices"][0]["message"]["content"]
+
+        self.state.assistant_reply = answer
+        self.state.messages.append({"role": "assistant", "content": answer})
+
+        # Optional: store key turns in long-term memory for later recall
+        self.remember(
+            f"Session {self.state.session_id} turn {self.state.turn_count}: "
+            f"user={self.state.last_user_message} assistant={answer}",
+            scope=f"/chat/{self.state.session_id}",
+        )
+        return answer
+```
+
+## Step 3: Run it
+
+```python Code
+flow = ChatHistoryFlow()
+
+first = flow.kickoff(
+    inputs={
+        "session_id": "customer-42",
+        "last_user_message": "I need help choosing a pricing plan for a 10-person team.",
+    }
+)
+print("Assistant:", first)
+
+second = flow.kickoff(
+    inputs={
+        "last_user_message": "We also need SSO and audit logs. What do you recommend now?",
+    }
+)
+print("Assistant:", second)
+print("Turns:", flow.state.turn_count)
+print("Recent messages:", len(flow.state.messages))
+```
+
+## Expected output (shape)
+
+```text Output
+Assistant: ...initial recommendation...
+Assistant: ...updated recommendation with SSO and audit-log requirements...
+Turns: 2
+Recent messages: 4
+```
+
+## Troubleshooting
+
+- If replies ignore earlier context:
+  increase `max_recent_messages` and ensure `running_summary` is included in the system context.
+- If prompts become too large:
+  lower `max_recent_messages` and summarize more aggressively.
+- If sessions collide:
+  provide a stable `session_id` and isolate memory scope with `/chat/{session_id}`.
+
+## Next steps
+
+- Add tool calls for account lookup or product catalog retrieval
+- Route to human review for high-risk decisions
+- Add structured output to capture recommendations in machine-readable JSON

docs/en/learn/human-feedback-in-flows.mdx

@@ -73,6 +73,8 @@ When this flow runs, it will:
 | `default_outcome` | `str` | No | Outcome to use if no feedback provided. Must be in `emit` |
 | `metadata` | `dict` | No | Additional data for enterprise integrations |
 | `provider` | `HumanFeedbackProvider` | No | Custom provider for async/non-blocking feedback. See [Async Human Feedback](#async-human-feedback-non-blocking) |
+| `learn` | `bool` | No | Enable HITL learning: distill lessons from feedback and pre-review future output. Default `False`. See [Learning from Feedback](#learning-from-feedback) |
+| `learn_limit` | `int` | No | Max past lessons to recall for pre-review. Default `5` |
 
 ### Basic Usage (No Routing)
 
@@ -96,33 +98,43 @@ def handle_feedback(self, result):
 When you specify `emit`, the decorator becomes a router. The human's free-form feedback is interpreted by an LLM and collapsed into one of the specified outcomes:
 
 ```python Code
-@start()
-@human_feedback(
-    message="Do you approve this content for publication?",
-    emit=["approved", "rejected", "needs_revision"],
-    llm="gpt-4o-mini",
-    default_outcome="needs_revision",
-)
-def review_content(self):
-    return "Draft blog post content here..."
+from crewai.flow.flow import Flow, start, listen, or_
+from crewai.flow.human_feedback import human_feedback
 
-@listen("approved")
-def publish(self, result):
-    print(f"Publishing! User said: {result.feedback}")
+class ReviewFlow(Flow):
+    @start()
+    def generate_content(self):
+        return "Draft blog post content here..."
 
-@listen("rejected")
-def discard(self, result):
-    print(f"Discarding. Reason: {result.feedback}")
+    @human_feedback(
+        message="Do you approve this content for publication?",
+        emit=["approved", "rejected", "needs_revision"],
+        llm="gpt-4o-mini",
+        default_outcome="needs_revision",
+    )
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "Draft blog post content here..."
 
-@listen("needs_revision")
-def revise(self, result):
-    print(f"Revising based on: {result.feedback}")
+    @listen("approved")
+    def publish(self, result):
+        print(f"Publishing! User said: {result.feedback}")
+
+    @listen("rejected")
+    def discard(self, result):
+        print(f"Discarding. Reason: {result.feedback}")
 ```
 
+When the human says something like "needs more detail", the LLM collapses that to `"needs_revision"`, which triggers `review_content` again via `or_()` — creating a revision loop. The loop continues until the outcome is `"approved"` or `"rejected"`.
+
 <Tip>
 The LLM uses structured outputs (function calling) when available to guarantee the response is one of your specified outcomes. This makes routing reliable and predictable.
 </Tip>
 
+<Warning>
+A `@start()` method only runs once at the beginning of the flow. If you need a revision loop, separate the start method from the review method and use `@listen(or_("trigger", "revision_outcome"))` on the review method to enable the self-loop.
+</Warning>
+
 ## HumanFeedbackResult
 
 The `HumanFeedbackResult` dataclass contains all information about a human feedback interaction:
@@ -186,127 +198,183 @@ Each `HumanFeedbackResult` is appended to `human_feedback_history`, so multiple
 
 ## Complete Example: Content Approval Workflow
 
-Here's a full example implementing a content review and approval workflow:
+Here's a full example implementing a content review and approval workflow with a revision loop:
 
 <CodeGroup>
 
 ```python Code
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 from pydantic import BaseModel
 
 
 class ContentState(BaseModel):
-    topic: str = ""
     draft: str = ""
-    final_content: str = ""
     revision_count: int = 0
+    status: str = "pending"
 
 
 class ContentApprovalFlow(Flow[ContentState]):
-    """A flow that generates content and gets human approval."""
+    """A flow that generates content and loops until the human approves."""
 
     @start()
-    def get_topic(self):
-        self.state.topic = input("What topic should I write about? ")
-        return self.state.topic
-
-    @listen(get_topic)
-    def generate_draft(self, topic):
-        # In real use, this would call an LLM
-        self.state.draft = f"# {topic}\n\nThis is a draft about {topic}..."
+    def generate_draft(self):
+        self.state.draft = "# AI Safety\n\nThis is a draft about AI Safety..."
         return self.state.draft
 
-    @listen(generate_draft)
     @human_feedback(
-        message="Please review this draft. Reply 'approved', 'rejected', or provide revision feedback:",
+        message="Please review this draft. Approve, reject, or describe what needs changing:",
         emit=["approved", "rejected", "needs_revision"],
         llm="gpt-4o-mini",
         default_outcome="needs_revision",
     )
-    def review_draft(self, draft):
-        return draft
+    @listen(or_("generate_draft", "needs_revision"))
+    def review_draft(self):
+        self.state.revision_count += 1
+        return f"{self.state.draft} (v{self.state.revision_count})"
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
-        self.state.final_content = result.output
-        print("\n✅ Content approved and published!")
-        print(f"Reviewer comment: {result.feedback}")
+        self.state.status = "published"
+        print(f"Content approved and published! Reviewer said: {result.feedback}")
         return "published"
 
     @listen("rejected")
     def handle_rejection(self, result: HumanFeedbackResult):
-        print("\n❌ Content rejected")
-        print(f"Reason: {result.feedback}")
+        self.state.status = "rejected"
+        print(f"Content rejected. Reason: {result.feedback}")
         return "rejected"
 
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        self.state.revision_count += 1
-        print(f"\n📝 Revision #{self.state.revision_count} requested")
-        print(f"Feedback: {result.feedback}")
 
-        # In a real flow, you might loop back to generate_draft
-        # For this example, we just acknowledge
-        return "revision_requested"
-
-
-# Run the flow
 flow = ContentApprovalFlow()
 result = flow.kickoff()
-print(f"\nFlow completed. Revisions requested: {flow.state.revision_count}")
+print(f"\nFlow completed. Status: {flow.state.status}, Reviews: {flow.state.revision_count}")
 ```
 
 ```text Output
-What topic should I write about? AI Safety
+==================================================
+OUTPUT FOR REVIEW:
+==================================================
+# AI Safety
+
+This is a draft about AI Safety... (v1)
+==================================================
+
+Please review this draft. Approve, reject, or describe what needs changing:
+(Press Enter to skip, or type your feedback)
+
+Your feedback: Needs more detail on alignment research
 
 ==================================================
 OUTPUT FOR REVIEW:
 ==================================================
 # AI Safety
 
-This is a draft about AI Safety...
+This is a draft about AI Safety... (v2)
 ==================================================
 
-Please review this draft. Reply 'approved', 'rejected', or provide revision feedback:
+Please review this draft. Approve, reject, or describe what needs changing:
 (Press Enter to skip, or type your feedback)
 
 Your feedback: Looks good, approved!
 
-✅ Content approved and published!
-Reviewer comment: Looks good, approved!
+Content approved and published! Reviewer said: Looks good, approved!
 
-Flow completed. Revisions requested: 0
+Flow completed. Status: published, Reviews: 2
 ```
 
 </CodeGroup>
 
+The key pattern is `@listen(or_("generate_draft", "needs_revision"))` — the review method listens to both the initial trigger and its own revision outcome, creating a self-loop that repeats until the human approves or rejects.
+
 ## Combining with Other Decorators
 
-The `@human_feedback` decorator works with other flow decorators. Place it as the innermost decorator (closest to the function):
+The `@human_feedback` decorator works with `@start()`, `@listen()`, and `or_()`. Both decorator orderings work — the framework propagates attributes in both directions — but the recommended patterns are:
 
 ```python Code
-# Correct: @human_feedback is innermost (closest to the function)
+# One-shot review at the start of a flow (no self-loop)
 @start()
-@human_feedback(message="Review this:")
+@human_feedback(message="Review this:", emit=["approved", "rejected"], llm="gpt-4o-mini")
 def my_start_method(self):
     return "content"
 
+# Linear review on a listener (no self-loop)
 @listen(other_method)
-@human_feedback(message="Review this too:")
+@human_feedback(message="Review this too:", emit=["good", "bad"], llm="gpt-4o-mini")
 def my_listener(self, data):
     return f"processed: {data}"
+
+# Self-loop: review that can loop back for revisions
+@human_feedback(message="Approve or revise?", emit=["approved", "revise"], llm="gpt-4o-mini")
+@listen(or_("upstream_method", "revise"))
+def review_with_loop(self):
+    return "content for review"
 ```
 
-<Tip>
-Place `@human_feedback` as the innermost decorator (last/closest to the function) so it wraps the method directly and can capture the return value before passing to the flow system.
-</Tip>
+### Self-loop pattern
+
+To create a revision loop, the review method must listen to **both** an upstream trigger and its own revision outcome using `or_()`:
+
+```python Code
+@start()
+def generate(self):
+    return "initial draft"
+
+@human_feedback(
+    message="Approve or request changes?",
+    emit=["revise", "approved"],
+    llm="gpt-4o-mini",
+    default_outcome="approved",
+)
+@listen(or_("generate", "revise"))
+def review(self):
+    return "content"
+
+@listen("approved")
+def publish(self):
+    return "published"
+```
+
+When the outcome is `"revise"`, the flow routes back to `review` (because it listens to `"revise"` via `or_()`). When the outcome is `"approved"`, the flow continues to `publish`. This works because the flow engine exempts routers from the "fire once" rule, allowing them to re-execute on each loop iteration.
+
+### Chained routers
+
+A listener triggered by one router's outcome can itself be a router:
+
+```python Code
+@start()
+def generate(self):
+    return "draft content"
+
+@human_feedback(message="First review:", emit=["approved", "rejected"], llm="gpt-4o-mini")
+@listen("generate")
+def first_review(self):
+    return "draft content"
+
+@human_feedback(message="Final review:", emit=["publish", "hold"], llm="gpt-4o-mini")
+@listen("approved")
+def final_review(self, prev):
+    return "final content"
+
+@listen("publish")
+def on_publish(self, prev):
+    return "published"
+
+@listen("hold")
+def on_hold(self, prev):
+    return "held for later"
+```
+
+### Limitations
+
+- **`@start()` methods run once**: A `@start()` method cannot self-loop. If you need a revision cycle, use a separate `@start()` method as the entry point and put the `@human_feedback` on a `@listen()` method.
+- **No `@start()` + `@listen()` on the same method**: This is a Flow framework constraint. A method is either a start point or a listener, not both.
 
 ## Best Practices
 
 ### 1. Write Clear Request Messages
 
-The `request` parameter is what the human sees. Make it actionable:
+The `message` parameter is what the human sees. Make it actionable:
 
 ```python Code
 # ✅ Good - clear and actionable
@@ -514,9 +582,9 @@ class ContentPipeline(Flow):
     @start()
     @human_feedback(
         message="Approve this content for publication?",
-        emit=["approved", "rejected", "needs_revision"],
+        emit=["approved", "rejected"],
         llm="gpt-4o-mini",
-        default_outcome="needs_revision",
+        default_outcome="rejected",
         provider=SlackNotificationProvider("#content-reviews"),
     )
     def generate_content(self):
@@ -532,11 +600,6 @@ class ContentPipeline(Flow):
         print(f"Archived. Reason: {result.feedback}")
         return {"status": "archived"}
 
-    @listen("needs_revision")
-    def queue_revision(self, result):
-        print(f"Queued for revision: {result.feedback}")
-        return {"status": "revision_needed"}
-
 
 # Starting the flow (will pause and wait for Slack response)
 def start_content_pipeline():
@@ -576,6 +639,64 @@ If you're using an async web framework (FastAPI, aiohttp, Slack Bolt async mode)
 5. **Automatic persistence**: State is automatically saved when `HumanFeedbackPending` is raised and uses `SQLiteFlowPersistence` by default
 6. **Custom persistence**: Pass a custom persistence instance to `from_pending()` if needed
 
+## Learning from Feedback
+
+The `learn=True` parameter enables a feedback loop between human reviewers and the memory system. When enabled, the system progressively improves its outputs by learning from past human corrections.
+
+### How It Works
+
+1. **After feedback**: The LLM extracts generalizable lessons from the output + feedback and stores them in memory with `source="hitl"`. If the feedback is just approval (e.g. "looks good"), nothing is stored.
+2. **Before next review**: Past HITL lessons are recalled from memory and applied by the LLM to improve the output before the human sees it.
+
+Over time, the human sees progressively better pre-reviewed output because each correction informs future reviews.
+
+### Example
+
+```python Code
+class ArticleReviewFlow(Flow):
+    @start()
+    def generate_article(self):
+        return self.crew.kickoff(inputs={"topic": "AI Safety"}).raw
+
+    @human_feedback(
+        message="Review this article draft:",
+        emit=["approved", "needs_revision"],
+        llm="gpt-4o-mini",
+        learn=True,  # enable HITL learning
+    )
+    @listen(or_("generate_article", "needs_revision"))
+    def review_article(self):
+        return self.last_human_feedback.output if self.last_human_feedback else "article draft"
+
+    @listen("approved")
+    def publish(self):
+        print(f"Publishing: {self.last_human_feedback.output}")
+```
+
+**First run**: The human sees the raw output and says "Always include citations for factual claims." The lesson is distilled and stored in memory.
+
+**Second run**: The system recalls the citation lesson, pre-reviews the output to add citations, then shows the improved version. The human's job shifts from "fix everything" to "catch what the system missed."
+
+### Configuration
+
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `learn` | `False` | Enable HITL learning |
+| `learn_limit` | `5` | Max past lessons to recall for pre-review |
+
+### Key Design Decisions
+
+- **Same LLM for everything**: The `llm` parameter on the decorator is shared by outcome collapsing, lesson distillation, and pre-review. No need to configure multiple models.
+- **Structured output**: Both distillation and pre-review use function calling with Pydantic models when the LLM supports it, falling back to text parsing otherwise.
+- **Non-blocking storage**: Lessons are stored via `remember_many()` which runs in a background thread -- the flow continues immediately.
+- **Graceful degradation**: If the LLM fails during distillation, nothing is stored. If it fails during pre-review, the raw output is shown. Neither failure blocks the flow.
+- **No scope/categories needed**: When storing lessons, only `source` is passed. The encoding pipeline infers scope, categories, and importance automatically.
+
+<Note>
+`learn=True` requires the Flow to have memory available. Flows get memory automatically by default, but if you've disabled it with `_skip_auto_memory`, HITL learning will be silently skipped.
+</Note>
+
+
 ## Related Documentation
 
 - [Flows Overview](/en/concepts/flows) - Learn about CrewAI Flows
@@ -583,3 +704,4 @@ If you're using an async web framework (FastAPI, aiohttp, Slack Bolt async mode)
 - [Flow Persistence](/en/concepts/flows#persistence) - Persisting flow state
 - [Routing with @router](/en/concepts/flows#router) - More about conditional routing
 - [Human Input on Execution](/en/learn/human-input-on-execution) - Task-level human input
+- [Memory](/en/concepts/memory) - The unified memory system used by HITL learning

docs/en/tools/database-data/nl2sqltool.mdx

@@ -15,6 +15,29 @@ Along with that provides the ability for the Agent to update the database based
 
 **Attention**: Make sure that the Agent has access to a Read-Replica or that is okay for the Agent to run insert/update queries on the database.
 
+## Security Model
+
+`NL2SQLTool` is an execution-capable tool. It runs model-generated SQL directly against the configured database connection.
+
+This means risk depends on your deployment choices:
+
+- Which credentials you provide in `db_uri`
+- Whether untrusted input can influence prompts
+- Whether you add tool-call guardrails before execution
+
+If you route untrusted input to agents using this tool, treat it as a high-risk integration.
+
+## Hardening Recommendations
+
+Use all of the following in production:
+
+- Use a read-only database user whenever possible
+- Prefer a read replica for analytics/retrieval workloads
+- Grant least privilege (no superuser/admin roles, no file/system-level capabilities)
+- Apply database-side resource limits (statement timeout, lock timeout, cost/row limits)
+- Add `before_tool_call` hooks to enforce allowed query patterns
+- Enable query logging and alerting for destructive statements
+
 ## Requirements
 
 - SqlAlchemy

docs/ko/enterprise/features/flow-hitl-management.mdx

@@ -38,22 +38,21 @@ CrewAI Enterprise는 AI 워크플로우를 협업적인 인간-AI 프로세스
 `@human_feedback` 데코레이터를 사용하여 Flow 내에 인간 검토 체크포인트를 구성합니다. 실행이 검토 포인트에 도달하면 시스템이 일시 중지되고, 담당자에게 이메일로 알리며, 응답을 기다립니다.
 
 ```python
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 
 class ContentApprovalFlow(Flow):
     @start()
     def generate_content(self):
-        # AI가 콘텐츠 생성
         return "Q1 캠페인용 마케팅 카피 생성..."
 
-    @listen(generate_content)
     @human_feedback(
         message="브랜드 준수를 위해 이 콘텐츠를 검토해 주세요:",
         emit=["approved", "rejected", "needs_revision"],
     )
-    def review_content(self, content):
-        return content
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "검토용 마케팅 카피..."
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
@@ -62,10 +61,6 @@ class ContentApprovalFlow(Flow):
     @listen("rejected")
     def archive_content(self, result: HumanFeedbackResult):
         print(f"콘텐츠 거부됨. 사유: {result.feedback}")
-
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        print(f"수정 요청: {result.feedback}")
 ```
 
 완전한 구현 세부 사항은 [Flow에서 인간 피드백](/ko/learn/human-feedback-in-flows) 가이드를 참조하세요.

docs/ko/enterprise/integrations/google_contacts.mdx

@@ -200,6 +200,25 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `clientData` (array, 선택사항): 클라이언트별 데이터. 각 항목은 `key` (string)와 `value` (string)가 있는 객체.
 
   </Accordion>
+
+  <Accordion title="google_contacts/update_contact_group">
+    **설명:** 연락처 그룹의 정보를 업데이트합니다.
+
+    **매개변수:**
+    - `resourceName` (string, 필수): 연락처 그룹의 리소스 이름 (예: 'contactGroups/myContactGroup').
+    - `name` (string, 필수): 연락처 그룹의 이름.
+    - `clientData` (array, 선택사항): 클라이언트별 데이터. 각 항목은 `key` (string)와 `value` (string)가 있는 객체.
+
+  </Accordion>
+
+  <Accordion title="google_contacts/delete_contact_group">
+    **설명:** 연락처 그룹을 삭제합니다.
+
+    **매개변수:**
+    - `resourceName` (string, 필수): 삭제할 연락처 그룹의 리소스 이름 (예: 'contactGroups/myContactGroup').
+    - `deleteContacts` (boolean, 선택사항): 그룹 내 연락처도 삭제할지 여부. 기본값: false
+
+  </Accordion>
 </AccordionGroup>
 
 ## 사용 예제

docs/ko/enterprise/integrations/google_docs.mdx

@@ -131,6 +131,297 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `endIndex` (integer, 필수): 범위의 끝 인덱스.
 
   </Accordion>
+
+  <Accordion title="google_docs/create_document_with_content">
+    **설명:** 내용이 포함된 새 Google 문서를 한 번에 만듭니다.
+
+    **매개변수:**
+    - `title` (string, 필수): 새 문서의 제목. 문서 상단과 Google Drive에 표시됩니다.
+    - `content` (string, 선택사항): 문서에 삽입할 텍스트 내용. 새 단락에는 `\n`을 사용하세요.
+
+  </Accordion>
+
+  <Accordion title="google_docs/append_text">
+    **설명:** Google 문서의 끝에 텍스트를 추가합니다. 인덱스를 지정할 필요 없이 자동으로 문서 끝에 삽입됩니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): create_document 응답 또는 URL에서 가져온 문서 ID.
+    - `text` (string, 필수): 문서 끝에 추가할 텍스트. 새 단락에는 `\n`을 사용하세요.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_bold">
+    **설명:** Google 문서에서 텍스트를 굵게 만들거나 굵게 서식을 제거합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 서식을 지정할 텍스트의 시작 위치.
+    - `endIndex` (integer, 필수): 서식을 지정할 텍스트의 끝 위치 (배타적).
+    - `bold` (boolean, 필수): 굵게 만들려면 `true`, 굵게를 제거하려면 `false`로 설정.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_italic">
+    **설명:** Google 문서에서 텍스트를 기울임꼴로 만들거나 기울임꼴 서식을 제거합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 서식을 지정할 텍스트의 시작 위치.
+    - `endIndex` (integer, 필수): 서식을 지정할 텍스트의 끝 위치 (배타적).
+    - `italic` (boolean, 필수): 기울임꼴로 만들려면 `true`, 기울임꼴을 제거하려면 `false`로 설정.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_underline">
+    **설명:** Google 문서에서 텍스트에 밑줄 서식을 추가하거나 제거합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 서식을 지정할 텍스트의 시작 위치.
+    - `endIndex` (integer, 필수): 서식을 지정할 텍스트의 끝 위치 (배타적).
+    - `underline` (boolean, 필수): 밑줄을 추가하려면 `true`, 밑줄을 제거하려면 `false`로 설정.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_strikethrough">
+    **설명:** Google 문서에서 텍스트에 취소선 서식을 추가하거나 제거합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 서식을 지정할 텍스트의 시작 위치.
+    - `endIndex` (integer, 필수): 서식을 지정할 텍스트의 끝 위치 (배타적).
+    - `strikethrough` (boolean, 필수): 취소선을 추가하려면 `true`, 제거하려면 `false`로 설정.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_font_size">
+    **설명:** Google 문서에서 텍스트의 글꼴 크기를 변경합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 서식을 지정할 텍스트의 시작 위치.
+    - `endIndex` (integer, 필수): 서식을 지정할 텍스트의 끝 위치 (배타적).
+    - `fontSize` (number, 필수): 포인트 단위의 글꼴 크기. 일반적인 크기: 10, 11, 12, 14, 16, 18, 24, 36.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_color">
+    **설명:** Google 문서에서 RGB 값(0-1 스케일)을 사용하여 텍스트 색상을 변경합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 서식을 지정할 텍스트의 시작 위치.
+    - `endIndex` (integer, 필수): 서식을 지정할 텍스트의 끝 위치 (배타적).
+    - `red` (number, 필수): 빨강 구성 요소 (0-1). 예: `1`은 완전한 빨강.
+    - `green` (number, 필수): 초록 구성 요소 (0-1). 예: `0.5`는 절반 초록.
+    - `blue` (number, 필수): 파랑 구성 요소 (0-1). 예: `0`은 파랑 없음.
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_hyperlink">
+    **설명:** Google 문서에서 기존 텍스트를 클릭 가능한 하이퍼링크로 변환합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 링크로 만들 텍스트의 시작 위치.
+    - `endIndex` (integer, 필수): 링크로 만들 텍스트의 끝 위치 (배타적).
+    - `url` (string, 필수): 링크가 가리킬 URL. 예: `"https://example.com"`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/apply_heading_style">
+    **설명:** Google 문서에서 텍스트 범위에 제목 또는 단락 스타일을 적용합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 스타일을 적용할 단락의 시작 위치.
+    - `endIndex` (integer, 필수): 스타일을 적용할 단락의 끝 위치.
+    - `style` (string, 필수): 적용할 스타일. 옵션: `NORMAL_TEXT`, `TITLE`, `SUBTITLE`, `HEADING_1`, `HEADING_2`, `HEADING_3`, `HEADING_4`, `HEADING_5`, `HEADING_6`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_paragraph_alignment">
+    **설명:** Google 문서에서 단락의 텍스트 정렬을 설정합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 정렬할 단락의 시작 위치.
+    - `endIndex` (integer, 필수): 정렬할 단락의 끝 위치.
+    - `alignment` (string, 필수): 텍스트 정렬. 옵션: `START` (왼쪽), `CENTER`, `END` (오른쪽), `JUSTIFIED`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_line_spacing">
+    **설명:** Google 문서에서 단락의 줄 간격을 설정합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 단락의 시작 위치.
+    - `endIndex` (integer, 필수): 단락의 끝 위치.
+    - `lineSpacing` (number, 필수): 백분율로 나타낸 줄 간격. `100` = 단일, `115` = 1.15배, `150` = 1.5배, `200` = 이중.
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_paragraph_bullets">
+    **설명:** Google 문서에서 단락을 글머리 기호 또는 번호 매기기 목록으로 변환합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 목록으로 변환할 단락의 시작 위치.
+    - `endIndex` (integer, 필수): 목록으로 변환할 단락의 끝 위치.
+    - `bulletPreset` (string, 필수): 글머리 기호/번호 매기기 스타일. 옵션: `BULLET_DISC_CIRCLE_SQUARE`, `BULLET_DIAMONDX_ARROW3D_SQUARE`, `BULLET_CHECKBOX`, `BULLET_ARROW_DIAMOND_DISC`, `BULLET_STAR_CIRCLE_SQUARE`, `NUMBERED_DECIMAL_ALPHA_ROMAN`, `NUMBERED_DECIMAL_ALPHA_ROMAN_PARENS`, `NUMBERED_DECIMAL_NESTED`, `NUMBERED_UPPERALPHA_ALPHA_ROMAN`, `NUMBERED_UPPERROMAN_UPPERALPHA_DECIMAL`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_paragraph_bullets">
+    **설명:** Google 문서에서 단락의 글머리 기호 또는 번호 매기기를 제거합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `startIndex` (integer, 필수): 목록 단락의 시작 위치.
+    - `endIndex` (integer, 필수): 목록 단락의 끝 위치.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_table_with_content">
+    **설명:** Google 문서에 내용이 포함된 표를 한 번에 삽입합니다. 내용은 2D 배열로 제공하세요.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `rows` (integer, 필수): 표의 행 수.
+    - `columns` (integer, 필수): 표의 열 수.
+    - `index` (integer, 선택사항): 표를 삽입할 위치. 제공하지 않으면 문서 끝에 삽입됩니다.
+    - `content` (array, 필수): 2D 배열로 된 표 내용. 각 내부 배열은 행입니다. 예: `[["Year", "Revenue"], ["2023", "$43B"], ["2024", "$45B"]]`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_table_row">
+    **설명:** 기존 표의 참조 셀 위 또는 아래에 새 행을 삽입합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `tableStartIndex` (integer, 필수): 표의 시작 인덱스. get_document에서 가져오세요.
+    - `rowIndex` (integer, 필수): 참조 셀의 행 인덱스 (0 기반).
+    - `columnIndex` (integer, 선택사항): 참조 셀의 열 인덱스 (0 기반). 기본값: `0`.
+    - `insertBelow` (boolean, 선택사항): `true`이면 참조 행 아래에, `false`이면 위에 삽입. 기본값: `true`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_table_column">
+    **설명:** 기존 표의 참조 셀 왼쪽 또는 오른쪽에 새 열을 삽입합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `tableStartIndex` (integer, 필수): 표의 시작 인덱스.
+    - `rowIndex` (integer, 선택사항): 참조 셀의 행 인덱스 (0 기반). 기본값: `0`.
+    - `columnIndex` (integer, 필수): 참조 셀의 열 인덱스 (0 기반).
+    - `insertRight` (boolean, 선택사항): `true`이면 오른쪽에, `false`이면 왼쪽에 삽입. 기본값: `true`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_table_row">
+    **설명:** Google 문서의 기존 표에서 행을 삭제합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `tableStartIndex` (integer, 필수): 표의 시작 인덱스.
+    - `rowIndex` (integer, 필수): 삭제할 행 인덱스 (0 기반).
+    - `columnIndex` (integer, 선택사항): 행의 아무 셀의 열 인덱스 (0 기반). 기본값: `0`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_table_column">
+    **설명:** Google 문서의 기존 표에서 열을 삭제합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `tableStartIndex` (integer, 필수): 표의 시작 인덱스.
+    - `rowIndex` (integer, 선택사항): 열의 아무 셀의 행 인덱스 (0 기반). 기본값: `0`.
+    - `columnIndex` (integer, 필수): 삭제할 열 인덱스 (0 기반).
+
+  </Accordion>
+
+  <Accordion title="google_docs/merge_table_cells">
+    **설명:** 표 셀 범위를 단일 셀로 병합합니다. 모든 셀의 내용이 보존됩니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `tableStartIndex` (integer, 필수): 표의 시작 인덱스.
+    - `rowIndex` (integer, 필수): 병합의 시작 행 인덱스 (0 기반).
+    - `columnIndex` (integer, 필수): 병합의 시작 열 인덱스 (0 기반).
+    - `rowSpan` (integer, 필수): 병합할 행 수.
+    - `columnSpan` (integer, 필수): 병합할 열 수.
+
+  </Accordion>
+
+  <Accordion title="google_docs/unmerge_table_cells">
+    **설명:** 이전에 병합된 표 셀을 개별 셀로 분리합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `tableStartIndex` (integer, 필수): 표의 시작 인덱스.
+    - `rowIndex` (integer, 필수): 병합된 셀의 행 인덱스 (0 기반).
+    - `columnIndex` (integer, 필수): 병합된 셀의 열 인덱스 (0 기반).
+    - `rowSpan` (integer, 필수): 병합된 셀이 차지하는 행 수.
+    - `columnSpan` (integer, 필수): 병합된 셀이 차지하는 열 수.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_inline_image">
+    **설명:** 공개 URL에서 Google 문서에 이미지를 삽입합니다. 이미지는 공개적으로 접근 가능해야 하고, 50MB 미만이며, PNG/JPEG/GIF 형식이어야 합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `uri` (string, 필수): 이미지의 공개 URL. 인증 없이 접근 가능해야 합니다.
+    - `index` (integer, 선택사항): 이미지를 삽입할 위치. 제공하지 않으면 문서 끝에 삽입됩니다. 기본값: `1`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_section_break">
+    **설명:** 서로 다른 서식을 가진 문서 섹션을 만들기 위해 섹션 나누기를 삽입합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `index` (integer, 필수): 섹션 나누기를 삽입할 위치.
+    - `sectionType` (string, 필수): 섹션 나누기의 유형. 옵션: `CONTINUOUS` (같은 페이지에 유지), `NEXT_PAGE` (새 페이지 시작).
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_header">
+    **설명:** 문서의 머리글을 만듭니다. insert_text를 사용하여 머리글 내용을 추가할 수 있는 headerId를 반환합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `type` (string, 선택사항): 머리글 유형. 옵션: `DEFAULT`. 기본값: `DEFAULT`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_footer">
+    **설명:** 문서의 바닥글을 만듭니다. insert_text를 사용하여 바닥글 내용을 추가할 수 있는 footerId를 반환합니다.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `type` (string, 선택사항): 바닥글 유형. 옵션: `DEFAULT`. 기본값: `DEFAULT`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_header">
+    **설명:** 문서에서 머리글을 삭제합니다. headerId를 찾으려면 get_document를 사용하세요.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `headerId` (string, 필수): 삭제할 머리글 ID. get_document 응답에서 가져오세요.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_footer">
+    **설명:** 문서에서 바닥글을 삭제합니다. footerId를 찾으려면 get_document를 사용하세요.
+
+    **매개변수:**
+    - `documentId` (string, 필수): 문서 ID.
+    - `footerId` (string, 필수): 삭제할 바닥글 ID. get_document 응답에서 가져오세요.
+
+  </Accordion>
 </AccordionGroup>
 
 ## 사용 예제

docs/ko/enterprise/integrations/google_slides.mdx

@@ -61,6 +61,22 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="google_slides/get_presentation_metadata">
+    **설명:** 프레젠테이션에 대한 가벼운 메타데이터(제목, 슬라이드 수, 슬라이드 ID)를 가져옵니다. 전체 콘텐츠를 가져오기 전에 먼저 사용하세요.
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 검색할 프레젠테이션의 ID.
+
+  </Accordion>
+
+  <Accordion title="google_slides/get_presentation_text">
+    **설명:** 프레젠테이션에서 모든 텍스트 콘텐츠를 추출합니다. 슬라이드 ID와 도형 및 테이블의 텍스트만 반환합니다 (포맷팅 없음).
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+
+  </Accordion>
+
   <Accordion title="google_slides/get_presentation">
     **설명:** ID로 프레젠테이션을 검색합니다.
 
@@ -80,6 +96,15 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="google_slides/get_slide_text">
+    **설명:** 단일 슬라이드에서 텍스트 콘텐츠를 추출합니다. 도형 및 테이블의 텍스트만 반환합니다 (포맷팅 또는 스타일 없음).
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `pageObjectId` (string, 필수): 텍스트를 가져올 슬라이드/페이지의 ID.
+
+  </Accordion>
+
   <Accordion title="google_slides/get_page">
     **설명:** ID로 특정 페이지를 검색합니다.
 
@@ -98,6 +123,120 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="google_slides/create_slide">
+    **설명:** 프레젠테이션에 추가 빈 슬라이드를 추가합니다. 새 프레젠테이션에는 이미 빈 슬라이드가 하나 있습니다. 먼저 get_presentation_metadata를 확인하세요. 제목/본문 영역이 있는 슬라이드는 create_slide_with_layout을 사용하세요.
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `insertionIndex` (integer, 선택사항): 슬라이드를 삽입할 위치 (0 기반). 생략하면 맨 끝에 추가됩니다.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_slide_with_layout">
+    **설명:** 제목, 본문 등의 플레이스홀더 영역이 있는 미리 정의된 레이아웃으로 슬라이드를 만듭니다. 구조화된 콘텐츠에는 create_slide보다 적합합니다. 생성 후 get_page로 플레이스홀더 ID를 찾고, 그 안에 텍스트를 삽입하세요.
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `layout` (string, 필수): 레이아웃 유형. 옵션: `BLANK`, `TITLE`, `TITLE_AND_BODY`, `TITLE_AND_TWO_COLUMNS`, `TITLE_ONLY`, `SECTION_HEADER`, `ONE_COLUMN_TEXT`, `MAIN_POINT`, `BIG_NUMBER`. 제목+설명은 TITLE_AND_BODY, 제목만은 TITLE, 섹션 구분은 SECTION_HEADER가 적합합니다.
+    - `insertionIndex` (integer, 선택사항): 삽입할 위치 (0 기반). 생략하면 맨 끝에 추가됩니다.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_text_box">
+    **설명:** 콘텐츠가 있는 텍스트 상자를 슬라이드에 만듭니다. 제목, 설명, 단락에 사용합니다. 테이블에는 사용하지 마세요. 선택적으로 EMU 단위로 위치(x, y)와 크기(width, height)를 지정할 수 있습니다 (914400 EMU = 1 인치).
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `slideId` (string, 필수): 텍스트 상자를 추가할 슬라이드의 ID.
+    - `text` (string, 필수): 텍스트 상자의 텍스트 내용.
+    - `x` (integer, 선택사항): EMU 단위 X 위치 (914400 = 1 인치). 기본값: 914400 (왼쪽에서 1 인치).
+    - `y` (integer, 선택사항): EMU 단위 Y 위치 (914400 = 1 인치). 기본값: 914400 (위에서 1 인치).
+    - `width` (integer, 선택사항): EMU 단위 너비. 기본값: 7315200 (약 8 인치).
+    - `height` (integer, 선택사항): EMU 단위 높이. 기본값: 914400 (약 1 인치).
+
+  </Accordion>
+
+  <Accordion title="google_slides/delete_slide">
+    **설명:** 프레젠테이션에서 슬라이드를 제거합니다. 슬라이드 ID를 찾으려면 먼저 get_presentation을 사용하세요.
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `slideId` (string, 필수): 삭제할 슬라이드의 객체 ID. get_presentation에서 가져옵니다.
+
+  </Accordion>
+
+  <Accordion title="google_slides/duplicate_slide">
+    **설명:** 기존 슬라이드의 복사본을 만듭니다. 복사본은 원본 바로 다음에 삽입됩니다.
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `slideId` (string, 필수): 복제할 슬라이드의 객체 ID. get_presentation에서 가져옵니다.
+
+  </Accordion>
+
+  <Accordion title="google_slides/move_slides">
+    **설명:** 슬라이드를 새 위치로 이동하여 순서를 변경합니다. 슬라이드 ID는 현재 프레젠테이션 순서대로 있어야 합니다 (중복 없음).
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `slideIds` (string 배열, 필수): 이동할 슬라이드 ID 배열. 현재 프레젠테이션 순서대로 있어야 합니다.
+    - `insertionIndex` (integer, 필수): 대상 위치 (0 기반). 0 = 맨 앞, 슬라이드 수 = 맨 끝.
+
+  </Accordion>
+
+  <Accordion title="google_slides/insert_youtube_video">
+    **설명:** 슬라이드에 YouTube 동영상을 삽입합니다. 동영상 ID는 YouTube URL의 "v=" 다음 값입니다 (예: youtube.com/watch?v=abc123의 경우 "abc123" 사용).
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `slideId` (string, 필수): 동영상을 추가할 슬라이드의 ID. get_presentation에서 가져옵니다.
+    - `videoId` (string, 필수): YouTube 동영상 ID (URL의 v= 다음 값).
+
+  </Accordion>
+
+  <Accordion title="google_slides/insert_drive_video">
+    **설명:** 슬라이드에 Google Drive의 동영상을 삽입합니다. 파일 ID는 Drive 파일 URL에서 찾을 수 있습니다.
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `slideId` (string, 필수): 동영상을 추가할 슬라이드의 ID. get_presentation에서 가져옵니다.
+    - `fileId` (string, 필수): 동영상의 Google Drive 파일 ID.
+
+  </Accordion>
+
+  <Accordion title="google_slides/set_slide_background_image">
+    **설명:** 슬라이드의 배경 이미지를 설정합니다. 이미지 URL은 공개적으로 액세스 가능해야 합니다.
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `slideId` (string, 필수): 배경을 설정할 슬라이드의 ID. get_presentation에서 가져옵니다.
+    - `imageUrl` (string, 필수): 배경으로 사용할 이미지의 공개적으로 액세스 가능한 URL.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_table">
+    **설명:** 슬라이드에 빈 테이블을 만듭니다. 콘텐츠가 있는 테이블을 만들려면 create_table_with_content를 사용하세요.
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `slideId` (string, 필수): 테이블을 추가할 슬라이드의 ID. get_presentation에서 가져옵니다.
+    - `rows` (integer, 필수): 테이블의 행 수.
+    - `columns` (integer, 필수): 테이블의 열 수.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_table_with_content">
+    **설명:** 한 번의 작업으로 콘텐츠가 있는 테이블을 만듭니다. 콘텐츠는 2D 배열로 제공하며, 각 내부 배열은 행을 나타냅니다. 예: [["Header1", "Header2"], ["Row1Col1", "Row1Col2"]].
+
+    **매개변수:**
+    - `presentationId` (string, 필수): 프레젠테이션의 ID.
+    - `slideId` (string, 필수): 테이블을 추가할 슬라이드의 ID. get_presentation에서 가져옵니다.
+    - `rows` (integer, 필수): 테이블의 행 수.
+    - `columns` (integer, 필수): 테이블의 열 수.
+    - `content` (array, 필수): 2D 배열 형태의 테이블 콘텐츠. 각 내부 배열은 행입니다. 예: [["Year", "Revenue"], ["2023", "$10M"]].
+
+  </Accordion>
+
   <Accordion title="google_slides/import_data_from_sheet">
     **설명:** Google 시트에서 프레젠테이션으로 데이터를 가져옵니다.
 

docs/ko/enterprise/integrations/microsoft_excel.mdx

@@ -148,6 +148,16 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="microsoft_excel/get_table_data">
+    **설명:** Excel 워크시트의 특정 테이블에서 데이터를 가져옵니다.
+
+    **매개변수:**
+    - `file_id` (string, 필수): Excel 파일의 ID.
+    - `worksheet_name` (string, 필수): 워크시트의 이름.
+    - `table_name` (string, 필수): 테이블의 이름.
+
+  </Accordion>
+
   <Accordion title="microsoft_excel/create_chart">
     **설명:** Excel 워크시트에 차트를 만듭니다.
 
@@ -180,6 +190,15 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="microsoft_excel/get_used_range_metadata">
+    **설명:** Excel 워크시트의 사용된 범위 메타데이터(크기만, 데이터 없음)를 가져옵니다.
+
+    **매개변수:**
+    - `file_id` (string, 필수): Excel 파일의 ID.
+    - `worksheet_name` (string, 필수): 워크시트의 이름.
+
+  </Accordion>
+
   <Accordion title="microsoft_excel/list_charts">
     **설명:** Excel 워크시트의 모든 차트를 가져옵니다.
 

docs/ko/enterprise/integrations/microsoft_onedrive.mdx

@@ -150,6 +150,49 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `item_id` (string, 필수): 파일의 ID.
 
   </Accordion>
+
+  <Accordion title="microsoft_onedrive/list_files_by_path">
+    **설명:** 특정 OneDrive 경로의 파일과 폴더를 나열합니다.
+
+    **매개변수:**
+    - `folder_path` (string, 필수): 폴더 경로 (예: 'Documents/Reports').
+    - `top` (integer, 선택사항): 검색할 항목 수 (최대 1000). 기본값: 50.
+    - `orderby` (string, 선택사항): 필드별 정렬 (예: "name asc", "lastModifiedDateTime desc"). 기본값: "name asc".
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/get_recent_files">
+    **설명:** OneDrive에서 최근에 액세스한 파일을 가져옵니다.
+
+    **매개변수:**
+    - `top` (integer, 선택사항): 검색할 항목 수 (최대 200). 기본값: 25.
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/get_shared_with_me">
+    **설명:** 사용자와 공유된 파일과 폴더를 가져옵니다.
+
+    **매개변수:**
+    - `top` (integer, 선택사항): 검색할 항목 수 (최대 200). 기본값: 50.
+    - `orderby` (string, 선택사항): 필드별 정렬. 기본값: "name asc".
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/get_file_by_path">
+    **설명:** 경로로 특정 파일 또는 폴더에 대한 정보를 가져옵니다.
+
+    **매개변수:**
+    - `file_path` (string, 필수): 파일 또는 폴더 경로 (예: 'Documents/report.docx').
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/download_file_by_path">
+    **설명:** 경로로 OneDrive에서 파일을 다운로드합니다.
+
+    **매개변수:**
+    - `file_path` (string, 필수): 파일 경로 (예: 'Documents/report.docx').
+
+  </Accordion>
 </AccordionGroup>
 
 ## 사용 예제
@@ -183,6 +226,62 @@ crew = Crew(
 crew.kickoff()
 ```
 
+### 파일 업로드 및 관리
+
+```python
+from crewai import Agent, Task, Crew
+
+# 파일 작업에 특화된 에이전트 생성
+file_operator = Agent(
+    role="파일 운영자",
+    goal="파일을 정확하게 업로드, 다운로드 및 관리",
+    backstory="파일 처리 및 콘텐츠 관리에 능숙한 AI 어시스턴트.",
+    apps=['microsoft_onedrive/upload_file', 'microsoft_onedrive/download_file', 'microsoft_onedrive/get_file_info']
+)
+
+# 파일 업로드 및 관리 작업
+file_management_task = Task(
+    description="'report.txt'라는 이름의 텍스트 파일을 'This is a sample report for the project.' 내용으로 업로드한 다음 업로드된 파일에 대한 정보를 가져오세요.",
+    agent=file_operator,
+    expected_output="파일이 성공적으로 업로드되고 파일 정보가 검색됨."
+)
+
+crew = Crew(
+    agents=[file_operator],
+    tasks=[file_management_task]
+)
+
+crew.kickoff()
+```
+
+### 파일 정리 및 공유
+
+```python
+from crewai import Agent, Task, Crew
+
+# 파일 정리 및 공유를 위한 에이전트 생성
+file_organizer = Agent(
+    role="파일 정리자",
+    goal="파일을 정리하고 협업을 위한 공유 링크 생성",
+    backstory="파일 정리 및 공유 권한 관리에 뛰어난 AI 어시스턴트.",
+    apps=['microsoft_onedrive/search_files', 'microsoft_onedrive/move_item', 'microsoft_onedrive/share_item', 'microsoft_onedrive/create_folder']
+)
+
+# 파일 정리 및 공유 작업
+organize_share_task = Task(
+    description="이름에 'presentation'이 포함된 파일을 검색하고, '프레젠테이션'이라는 폴더를 만든 다음, 찾은 파일을 이 폴더로 이동하고 폴더에 대한 읽기 전용 공유 링크를 생성하세요.",
+    agent=file_organizer,
+    expected_output="파일이 '프레젠테이션' 폴더로 정리되고 공유 링크가 생성됨."
+)
+
+crew = Crew(
+    agents=[file_organizer],
+    tasks=[organize_share_task]
+)
+
+crew.kickoff()
+```
+
 ## 문제 해결
 
 ### 일반적인 문제
@@ -196,6 +295,30 @@ crew.kickoff()
 
 - 파일 업로드 시 `file_name`과 `content`가 제공되는지 확인하세요.
 - 바이너리 파일의 경우 내용이 Base64로 인코딩되어야 합니다.
+- OneDrive에 대한 쓰기 권한이 있는지 확인하세요.
+
+**파일/폴더 ID 문제**
+
+- 특정 파일 또는 폴더에 액세스할 때 항목 ID가 올바른지 다시 확인하세요.
+- 항목 ID는 `list_files` 또는 `search_files`와 같은 다른 작업에서 반환됩니다.
+- 참조하는 항목이 존재하고 액세스 가능한지 확인하세요.
+
+**검색 및 필터 작업**
+
+- `search_files` 작업에 적절한 검색어를 사용하세요.
+- `filter` 매개변수의 경우 올바른 OData 문법을 사용하세요.
+
+**파일 작업 (복사/이동)**
+
+- `move_item`의 경우 `item_id`와 `parent_id`가 모두 제공되는지 확인하세요.
+- `copy_item`의 경우 `item_id`만 필요합니다. `parent_id`는 지정하지 않으면 루트로 기본 설정됩니다.
+- 대상 폴더가 존재하고 액세스 가능한지 확인하세요.
+
+**공유 링크 생성**
+
+- 공유 링크를 만들기 전에 항목이 존재하는지 확인하세요.
+- 공유 요구 사항에 따라 적절한 `type`과 `scope`를 선택하세요.
+- `anonymous` 범위는 로그인 없이 액세스를 허용합니다. `organization`은 조직 계정이 필요합니다.
 
 ### 도움 받기
 

docs/ko/enterprise/integrations/microsoft_outlook.mdx

@@ -132,6 +132,74 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `companyName` (string, 선택사항): 연락처의 회사 이름.
 
   </Accordion>
+
+  <Accordion title="microsoft_outlook/get_message">
+    **설명:** ID로 특정 이메일 메시지를 가져옵니다.
+
+    **매개변수:**
+    - `message_id` (string, 필수): 메시지의 고유 식별자. get_messages 작업에서 얻을 수 있습니다.
+    - `select` (string, 선택사항): 반환할 속성의 쉼표로 구분된 목록. 예: "id,subject,body,from,receivedDateTime". 기본값: "id,subject,body,from,toRecipients,receivedDateTime".
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/reply_to_email">
+    **설명:** 이메일 메시지에 회신합니다.
+
+    **매개변수:**
+    - `message_id` (string, 필수): 회신할 메시지의 고유 식별자. get_messages 작업에서 얻을 수 있습니다.
+    - `comment` (string, 필수): 회신 메시지 내용. 일반 텍스트 또는 HTML 가능. 원본 메시지가 이 내용 아래에 인용됩니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/forward_email">
+    **설명:** 이메일 메시지를 전달합니다.
+
+    **매개변수:**
+    - `message_id` (string, 필수): 전달할 메시지의 고유 식별자. get_messages 작업에서 얻을 수 있습니다.
+    - `to_recipients` (array, 필수): 전달할 받는 사람의 이메일 주소 배열. 예: ["john@example.com", "jane@example.com"].
+    - `comment` (string, 선택사항): 전달된 콘텐츠 위에 포함할 선택적 메시지. 일반 텍스트 또는 HTML 가능.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/mark_message_read">
+    **설명:** 메시지를 읽음 또는 읽지 않음으로 표시합니다.
+
+    **매개변수:**
+    - `message_id` (string, 필수): 메시지의 고유 식별자. get_messages 작업에서 얻을 수 있습니다.
+    - `is_read` (boolean, 필수): 읽음으로 표시하려면 true, 읽지 않음으로 표시하려면 false로 설정합니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/delete_message">
+    **설명:** 이메일 메시지를 삭제합니다.
+
+    **매개변수:**
+    - `message_id` (string, 필수): 삭제할 메시지의 고유 식별자. get_messages 작업에서 얻을 수 있습니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/update_event">
+    **설명:** 기존 캘린더 이벤트를 업데이트합니다.
+
+    **매개변수:**
+    - `event_id` (string, 필수): 이벤트의 고유 식별자. get_calendar_events 작업에서 얻을 수 있습니다.
+    - `subject` (string, 선택사항): 이벤트의 새 제목/제목.
+    - `start_time` (string, 선택사항): ISO 8601 형식의 새 시작 시간 (예: "2024-01-20T10:00:00"). 필수: 이 필드 사용 시 start_timezone도 제공해야 합니다.
+    - `start_timezone` (string, 선택사항): 시작 시간의 시간대. start_time 업데이트 시 필수. 예: "Pacific Standard Time", "Eastern Standard Time", "UTC".
+    - `end_time` (string, 선택사항): ISO 8601 형식의 새 종료 시간. 필수: 이 필드 사용 시 end_timezone도 제공해야 합니다.
+    - `end_timezone` (string, 선택사항): 종료 시간의 시간대. end_time 업데이트 시 필수. 예: "Pacific Standard Time", "Eastern Standard Time", "UTC".
+    - `location` (string, 선택사항): 이벤트의 새 위치.
+    - `body` (string, 선택사항): 이벤트의 새 본문/설명. HTML 형식 지원.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/delete_event">
+    **설명:** 캘린더 이벤트를 삭제합니다.
+
+    **매개변수:**
+    - `event_id` (string, 필수): 삭제할 이벤트의 고유 식별자. get_calendar_events 작업에서 얻을 수 있습니다.
+
+  </Accordion>
 </AccordionGroup>
 
 ## 사용 예제
@@ -165,6 +233,62 @@ crew = Crew(
 crew.kickoff()
 ```
 
+### 이메일 관리 및 검색
+
+```python
+from crewai import Agent, Task, Crew
+
+# 이메일 관리에 특화된 에이전트 생성
+email_manager = Agent(
+    role="이메일 관리자",
+    goal="이메일 메시지를 검색하고 가져와 정리",
+    backstory="이메일 정리 및 관리에 능숙한 AI 어시스턴트.",
+    apps=['microsoft_outlook/get_messages']
+)
+
+# 이메일 검색 및 가져오기 작업
+search_emails_task = Task(
+    description="최신 읽지 않은 이메일 20건을 가져와 가장 중요한 것들의 요약을 제공하세요.",
+    agent=email_manager,
+    expected_output="주요 읽지 않은 이메일의 요약과 핵심 세부 정보."
+)
+
+crew = Crew(
+    agents=[email_manager],
+    tasks=[search_emails_task]
+)
+
+crew.kickoff()
+```
+
+### 캘린더 및 연락처 관리
+
+```python
+from crewai import Agent, Task, Crew
+
+# 캘린더 및 연락처 관리를 위한 에이전트 생성
+scheduler = Agent(
+    role="캘린더 및 연락처 관리자",
+    goal="캘린더 이벤트를 관리하고 연락처 정보를 유지",
+    backstory="일정 관리 및 연락처 정리를 담당하는 AI 어시스턴트.",
+    apps=['microsoft_outlook/create_calendar_event', 'microsoft_outlook/get_calendar_events', 'microsoft_outlook/create_contact']
+)
+
+# 회의 생성 및 연락처 추가 작업
+schedule_task = Task(
+    description="내일 오후 2시 '팀 회의' 제목으로 '회의실 A' 장소의 캘린더 이벤트를 만들고, 'john.smith@example.com' 이메일과 '프로젝트 매니저' 직책으로 'John Smith'의 새 연락처를 추가하세요.",
+    agent=scheduler,
+    expected_output="캘린더 이벤트가 생성되고 새 연락처가 추가됨."
+)
+
+crew = Crew(
+    agents=[scheduler],
+    tasks=[schedule_task]
+)
+
+crew.kickoff()
+```
+
 ## 문제 해결
 
 ### 일반적인 문제
@@ -173,11 +297,29 @@ crew.kickoff()
 
 - Microsoft 계정이 이메일, 캘린더 및 연락처 액세스에 필요한 권한을 가지고 있는지 확인하세요.
 - 필요한 범위: `Mail.Read`, `Mail.Send`, `Calendars.Read`, `Calendars.ReadWrite`, `Contacts.Read`, `Contacts.ReadWrite`.
+- OAuth 연결에 필요한 모든 범위가 포함되어 있는지 확인하세요.
 
 **이메일 보내기 문제**
 
 - `send_email`에 `to_recipients`, `subject`, `body`가 제공되는지 확인하세요.
 - 이메일 주소가 올바르게 형식화되어 있는지 확인하세요.
+- 계정에 `Mail.Send` 권한이 있는지 확인하세요.
+
+**캘린더 이벤트 생성**
+
+- `subject`, `start_datetime`, `end_datetime`이 제공되는지 확인하세요.
+- 날짜/시간 필드에 적절한 ISO 8601 형식을 사용하세요 (예: '2024-01-20T10:00:00').
+- 이벤트가 잘못된 시간에 표시되는 경우 시간대 설정을 확인하세요.
+
+**연락처 관리**
+
+- `create_contact`의 경우 필수인 `displayName`이 제공되는지 확인하세요.
+- `emailAddresses`를 제공할 때 `address`와 `name` 속성이 있는 올바른 객체 형식을 사용하세요.
+
+**검색 및 필터 문제**
+
+- `filter` 매개변수에 올바른 OData 문법을 사용하세요.
+- 날짜 필터의 경우 ISO 8601 형식을 사용하세요 (예: "receivedDateTime ge '2024-01-01T00:00:00Z'").
 
 ### 도움 받기
 

docs/ko/enterprise/integrations/microsoft_sharepoint.mdx

@@ -77,6 +77,17 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
+  <Accordion title="microsoft_sharepoint/get_drives">
+    **설명:** SharePoint 사이트의 모든 문서 라이브러리(드라이브)를 나열합니다. 파일 작업을 사용하기 전에 사용 가능한 라이브러리를 찾으려면 이 작업을 사용하세요.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `top` (integer, 선택사항): 페이지당 반환할 최대 드라이브 수 (1-999). 기본값: 100
+    - `skip_token` (string, 선택사항): 다음 결과 페이지를 가져오기 위한 이전 응답의 페이지네이션 토큰.
+    - `select` (string, 선택사항): 반환할 속성의 쉼표로 구분된 목록 (예: 'id,name,webUrl,driveType').
+
+  </Accordion>
+
   <Accordion title="microsoft_sharepoint/get_site_lists">
     **설명:** SharePoint 사이트의 모든 목록을 가져옵니다.
 
@@ -145,20 +156,317 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
 
   </Accordion>
 
-  <Accordion title="microsoft_sharepoint/get_drive_items">
-    **설명:** SharePoint 문서 라이브러리에서 파일과 폴더를 가져옵니다.
+  <Accordion title="microsoft_sharepoint/list_files">
+    **설명:** SharePoint 문서 라이브러리에서 파일과 폴더를 가져옵니다. 기본적으로 루트 폴더를 나열하지만 folder_id를 제공하여 하위 폴더로 이동할 수 있습니다.
 
     **매개변수:**
-    - `site_id` (string, 필수): SharePoint 사이트의 ID.
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `folder_id` (string, 선택사항): 내용을 나열할 폴더의 ID. 루트 폴더의 경우 'root'를 사용하거나 이전 list_files 호출에서 가져온 폴더 ID를 제공하세요. 기본값: 'root'
+    - `top` (integer, 선택사항): 페이지당 반환할 최대 항목 수 (1-1000). 기본값: 50
+    - `skip_token` (string, 선택사항): 다음 결과 페이지를 가져오기 위한 이전 응답의 페이지네이션 토큰.
+    - `orderby` (string, 선택사항): 결과 정렬 순서 (예: 'name asc', 'size desc', 'lastModifiedDateTime desc'). 기본값: 'name asc'
+    - `filter` (string, 선택사항): 결과를 좁히기 위한 OData 필터 (예: 'file ne null'은 파일만, 'folder ne null'은 폴더만).
+    - `select` (string, 선택사항): 반환할 필드의 쉼표로 구분된 목록 (예: 'id,name,size,folder,file,webUrl,lastModifiedDateTime').
 
   </Accordion>
 
-  <Accordion title="microsoft_sharepoint/delete_drive_item">
-    **설명:** SharePoint 문서 라이브러리에서 파일 또는 폴더를 삭제합니다.
+  <Accordion title="microsoft_sharepoint/delete_file">
+    **설명:** SharePoint 문서 라이브러리에서 파일 또는 폴더를 삭제합니다. 폴더의 경우 모든 내용이 재귀적으로 삭제됩니다. 항목은 사이트 휴지통으로 이동됩니다.
 
     **매개변수:**
-    - `site_id` (string, 필수): SharePoint 사이트의 ID.
-    - `item_id` (string, 필수): 삭제할 파일 또는 폴더의 ID.
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): 삭제할 파일 또는 폴더의 고유 식별자. list_files에서 가져오세요.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/list_files_by_path">
+    **설명:** 경로로 SharePoint 문서 라이브러리 폴더의 파일과 폴더를 나열합니다. 깊은 탐색을 위해 여러 list_files 호출보다 더 효율적입니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `folder_path` (string, 필수): 앞뒤 슬래시 없이 폴더의 전체 경로 (예: 'Documents', 'Reports/2024/Q1').
+    - `top` (integer, 선택사항): 페이지당 반환할 최대 항목 수 (1-1000). 기본값: 50
+    - `skip_token` (string, 선택사항): 다음 결과 페이지를 가져오기 위한 이전 응답의 페이지네이션 토큰.
+    - `orderby` (string, 선택사항): 결과 정렬 순서 (예: 'name asc', 'size desc'). 기본값: 'name asc'
+    - `select` (string, 선택사항): 반환할 필드의 쉼표로 구분된 목록 (예: 'id,name,size,folder,file,webUrl,lastModifiedDateTime').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/download_file">
+    **설명:** SharePoint 문서 라이브러리에서 원시 파일 내용을 다운로드합니다. 일반 텍스트 파일(.txt, .csv, .json)에만 사용하세요. Excel 파일의 경우 Excel 전용 작업을 사용하세요. Word 파일의 경우 get_word_document_content를 사용하세요.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): 다운로드할 파일의 고유 식별자. list_files 또는 list_files_by_path에서 가져오세요.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_file_info">
+    **설명:** SharePoint 문서 라이브러리의 특정 파일 또는 폴더에 대한 자세한 메타데이터를 가져옵니다. 이름, 크기, 생성/수정 날짜 및 작성자 정보가 포함됩니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): 파일 또는 폴더의 고유 식별자. list_files 또는 list_files_by_path에서 가져오세요.
+    - `select` (string, 선택사항): 반환할 속성의 쉼표로 구분된 목록 (예: 'id,name,size,createdDateTime,lastModifiedDateTime,webUrl,createdBy,lastModifiedBy').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/create_folder">
+    **설명:** SharePoint 문서 라이브러리에 새 폴더를 만듭니다. 기본적으로 루트에 폴더를 만들며 하위 폴더를 만들려면 parent_id를 사용하세요.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `folder_name` (string, 필수): 새 폴더의 이름. 사용할 수 없는 문자: \ / : * ? " < > |
+    - `parent_id` (string, 선택사항): 상위 폴더의 ID. 문서 라이브러리 루트의 경우 'root'를 사용하거나 list_files에서 가져온 폴더 ID를 제공하세요. 기본값: 'root'
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/search_files">
+    **설명:** 키워드로 SharePoint 문서 라이브러리에서 파일과 폴더를 검색합니다. 파일 이름, 폴더 이름 및 Office 문서의 파일 내용을 검색합니다. 와일드카드나 특수 문자를 사용하지 마세요.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `query` (string, 필수): 검색 키워드 (예: 'report', 'budget 2024'). *.txt와 같은 와일드카드는 지원되지 않습니다.
+    - `top` (integer, 선택사항): 페이지당 반환할 최대 결과 수 (1-1000). 기본값: 50
+    - `skip_token` (string, 선택사항): 다음 결과 페이지를 가져오기 위한 이전 응답의 페이지네이션 토큰.
+    - `select` (string, 선택사항): 반환할 필드의 쉼표로 구분된 목록 (예: 'id,name,size,folder,file,webUrl,lastModifiedDateTime').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/copy_file">
+    **설명:** SharePoint 내에서 파일 또는 폴더를 새 위치로 복사합니다. 원본 항목은 변경되지 않습니다. 대용량 파일의 경우 복사 작업은 비동기적입니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): 복사할 파일 또는 폴더의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `destination_folder_id` (string, 필수): 대상 폴더의 ID. 루트 폴더의 경우 'root'를 사용하거나 list_files에서 가져온 폴더 ID를 사용하세요.
+    - `new_name` (string, 선택사항): 복사본의 새 이름. 제공하지 않으면 원래 이름이 사용됩니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/move_file">
+    **설명:** SharePoint 내에서 파일 또는 폴더를 새 위치로 이동합니다. 항목은 원래 위치에서 제거됩니다. 폴더의 경우 모든 내용도 함께 이동됩니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): 이동할 파일 또는 폴더의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `destination_folder_id` (string, 필수): 대상 폴더의 ID. 루트 폴더의 경우 'root'를 사용하거나 list_files에서 가져온 폴더 ID를 사용하세요.
+    - `new_name` (string, 선택사항): 이동된 항목의 새 이름. 제공하지 않으면 원래 이름이 유지됩니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_worksheets">
+    **설명:** SharePoint 문서 라이브러리에 저장된 Excel 통합 문서의 모든 워크시트(탭)를 나열합니다. 반환된 워크시트 이름을 다른 Excel 작업에 사용하세요.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `select` (string, 선택사항): 반환할 속성의 쉼표로 구분된 목록 (예: 'id,name,position,visibility').
+    - `filter` (string, 선택사항): OData 필터 표현식 (예: "visibility eq 'Visible'"로 숨겨진 시트 제외).
+    - `top` (integer, 선택사항): 반환할 최대 워크시트 수. 최소: 1, 최대: 999
+    - `orderby` (string, 선택사항): 정렬 순서 (예: 'position asc'로 탭 순서대로 반환).
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/create_excel_worksheet">
+    **설명:** SharePoint 문서 라이브러리에 저장된 Excel 통합 문서에 새 워크시트(탭)를 만듭니다. 새 시트는 탭 목록의 끝에 추가됩니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `name` (string, 필수): 새 워크시트의 이름. 최대 31자. 사용할 수 없는 문자: \ / * ? : [ ]. 통합 문서 내에서 고유해야 합니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_range_data">
+    **설명:** SharePoint에 저장된 Excel 워크시트의 특정 범위에서 셀 값을 가져옵니다. 크기를 모르는 상태에서 모든 데이터를 읽으려면 대신 get_excel_used_range를 사용하세요.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 읽을 워크시트(탭)의 이름. get_excel_worksheets에서 가져오세요. 대소문자를 구분합니다.
+    - `range` (string, 필수): A1 표기법의 셀 범위 (예: 'A1:C10', 'A:C', '1:5', 'A1').
+    - `select` (string, 선택사항): 반환할 속성의 쉼표로 구분된 목록 (예: 'address,values,formulas,numberFormat,text').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/update_excel_range_data">
+    **설명:** SharePoint에 저장된 Excel 워크시트의 특정 범위에 값을 씁니다. 기존 셀 내용을 덮어씁니다. values 배열의 크기는 범위 크기와 정확히 일치해야 합니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 업데이트할 워크시트(탭)의 이름. get_excel_worksheets에서 가져오세요. 대소문자를 구분합니다.
+    - `range` (string, 필수): 값을 쓸 A1 표기법의 셀 범위 (예: 'A1:C3'은 3x3 블록).
+    - `values` (array, 필수): 2D 값 배열 (셀을 포함하는 행). A1:B2의 예: [["Header1", "Header2"], ["Value1", "Value2"]]. 셀을 지우려면 null을 사용하세요.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_used_range_metadata">
+    **설명:** 실제 셀 값 없이 워크시트에서 사용된 범위의 메타데이터(주소 및 크기)만 반환합니다. 대용량 파일에서 데이터를 청크로 읽기 전에 스프레드시트 크기를 파악하는 데 이상적입니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 읽을 워크시트(탭)의 이름. get_excel_worksheets에서 가져오세요. 대소문자를 구분합니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_used_range">
+    **설명:** SharePoint에 저장된 워크시트에서 데이터가 포함된 모든 셀을 가져옵니다. 2MB보다 큰 파일에는 사용하지 마세요. 대용량 파일의 경우 먼저 get_excel_used_range_metadata를 사용한 다음 get_excel_range_data로 작은 청크로 읽으세요.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 읽을 워크시트(탭)의 이름. get_excel_worksheets에서 가져오세요. 대소문자를 구분합니다.
+    - `select` (string, 선택사항): 반환할 속성의 쉼표로 구분된 목록 (예: 'address,values,formulas,numberFormat,text,rowCount,columnCount').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_cell">
+    **설명:** SharePoint의 Excel 파일에서 행과 열 인덱스로 단일 셀의 값을 가져옵니다. 인덱스는 0 기반입니다 (행 0 = Excel 행 1, 열 0 = 열 A).
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 워크시트(탭)의 이름. get_excel_worksheets에서 가져오세요. 대소문자를 구분합니다.
+    - `row` (integer, 필수): 0 기반 행 인덱스 (행 0 = Excel 행 1). 유효 범위: 0-1048575
+    - `column` (integer, 필수): 0 기반 열 인덱스 (열 0 = A, 열 1 = B). 유효 범위: 0-16383
+    - `select` (string, 선택사항): 반환할 속성의 쉼표로 구분된 목록 (예: 'address,values,formulas,numberFormat,text').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/add_excel_table">
+    **설명:** 셀 범위를 필터링, 정렬 및 구조화된 데이터 기능이 있는 서식이 지정된 Excel 테이블로 변환합니다. 테이블을 만들면 add_excel_table_row로 데이터를 추가할 수 있습니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 데이터 범위가 포함된 워크시트의 이름. get_excel_worksheets에서 가져오세요.
+    - `range` (string, 필수): 헤더와 데이터를 포함하여 테이블로 변환할 셀 범위 (예: 'A1:D10'에서 A1:D1은 열 헤더).
+    - `has_headers` (boolean, 선택사항): 첫 번째 행에 열 헤더가 포함되어 있으면 true로 설정. 기본값: true
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_tables">
+    **설명:** SharePoint에 저장된 특정 Excel 워크시트의 모든 테이블을 나열합니다. id, name, showHeaders 및 showTotals를 포함한 테이블 속성을 반환합니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 테이블을 가져올 워크시트의 이름. get_excel_worksheets에서 가져오세요.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/add_excel_table_row">
+    **설명:** SharePoint 파일의 Excel 테이블 끝에 새 행을 추가합니다. values 배열은 테이블의 열 수와 같은 수의 요소를 가져야 합니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 테이블이 포함된 워크시트의 이름. get_excel_worksheets에서 가져오세요.
+    - `table_name` (string, 필수): 행을 추가할 테이블의 이름 (예: 'Table1'). get_excel_tables에서 가져오세요. 대소문자를 구분합니다.
+    - `values` (array, 필수): 새 행의 셀 값 배열로 테이블 순서대로 열당 하나씩 (예: ["John Doe", "john@example.com", 25]).
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_table_data">
+    **설명:** SharePoint 파일의 Excel 테이블에서 모든 행을 데이터 범위로 가져옵니다. 정확한 범위를 알 필요가 없으므로 구조화된 테이블 작업 시 get_excel_range_data보다 쉽습니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 테이블이 포함된 워크시트의 이름. get_excel_worksheets에서 가져오세요.
+    - `table_name` (string, 필수): 데이터를 가져올 테이블의 이름 (예: 'Table1'). get_excel_tables에서 가져오세요. 대소문자를 구분합니다.
+    - `select` (string, 선택사항): 반환할 속성의 쉼표로 구분된 목록 (예: 'address,values,formulas,numberFormat,text').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/create_excel_chart">
+    **설명:** SharePoint에 저장된 Excel 워크시트에 데이터 범위에서 차트 시각화를 만듭니다. 차트는 워크시트에 포함됩니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 차트를 만들 워크시트의 이름. get_excel_worksheets에서 가져오세요.
+    - `chart_type` (string, 필수): 차트 유형 (예: 'ColumnClustered', 'ColumnStacked', 'Line', 'LineMarkers', 'Pie', 'Bar', 'BarClustered', 'Area', 'Scatter', 'Doughnut').
+    - `source_data` (string, 필수): 헤더를 포함한 A1 표기법의 차트 데이터 범위 (예: 'A1:B10').
+    - `series_by` (string, 선택사항): 데이터 계열 구성 방법: 'Auto', 'Columns' 또는 'Rows'. 기본값: 'Auto'
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/list_excel_charts">
+    **설명:** SharePoint에 저장된 Excel 워크시트에 포함된 모든 차트를 나열합니다. id, name, chartType, height, width 및 position을 포함한 차트 속성을 반환합니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 차트를 나열할 워크시트의 이름. get_excel_worksheets에서 가져오세요.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/delete_excel_worksheet">
+    **설명:** SharePoint에 저장된 Excel 통합 문서에서 워크시트(탭)와 모든 내용을 영구적으로 제거합니다. 실행 취소할 수 없습니다. 통합 문서에는 최소 하나의 워크시트가 있어야 합니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 삭제할 워크시트의 이름. 대소문자를 구분합니다. 이 시트의 모든 데이터, 테이블 및 차트가 영구적으로 제거됩니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/delete_excel_table">
+    **설명:** SharePoint의 Excel 워크시트에서 테이블을 제거합니다. 테이블 구조(필터링, 서식, 테이블 기능)는 삭제되지만 기본 셀 데이터는 보존됩니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+    - `worksheet_name` (string, 필수): 테이블이 포함된 워크시트의 이름. get_excel_worksheets에서 가져오세요.
+    - `table_name` (string, 필수): 삭제할 테이블의 이름 (예: 'Table1'). get_excel_tables에서 가져오세요. 테이블 삭제 후에도 셀의 데이터는 유지됩니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/list_excel_names">
+    **설명:** SharePoint에 저장된 Excel 통합 문서에 정의된 모든 명명된 범위를 가져옵니다. 명명된 범위는 셀 범위에 대한 사용자 정의 레이블입니다 (예: 'SalesData'는 A1:D100을 가리킴).
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Excel 파일의 고유 식별자. list_files 또는 search_files에서 가져오세요.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_word_document_content">
+    **설명:** SharePoint 문서 라이브러리에 저장된 Word 문서(.docx)에서 텍스트 내용을 다운로드하고 추출합니다. SharePoint에서 Word 문서를 읽는 권장 방법입니다.
+
+    **매개변수:**
+    - `site_id` (string, 필수): get_sites에서 가져온 전체 SharePoint 사이트 식별자.
+    - `drive_id` (string, 필수): 문서 라이브러리의 ID. 먼저 get_drives를 호출하여 유효한 드라이브 ID를 가져오세요.
+    - `item_id` (string, 필수): SharePoint에 있는 Word 문서(.docx)의 고유 식별자. list_files 또는 search_files에서 가져오세요.
 
   </Accordion>
 </AccordionGroup>

docs/ko/enterprise/integrations/microsoft_teams.mdx

@@ -107,6 +107,86 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `join_web_url` (string, 필수): 검색할 회의의 웹 참가 URL.
 
   </Accordion>
+
+  <Accordion title="microsoft_teams/search_online_meetings_by_meeting_id">
+    **설명:** 외부 Meeting ID로 온라인 회의를 검색합니다.
+
+    **매개변수:**
+    - `join_meeting_id` (string, 필수): 참석자가 참가할 때 사용하는 회의 ID(숫자 코드). 회의 초대에 표시되는 joinMeetingId이며, Graph API meeting id가 아닙니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/get_meeting">
+    **설명:** 특정 온라인 회의의 세부 정보를 가져옵니다.
+
+    **매개변수:**
+    - `meeting_id` (string, 필수): Graph API 회의 ID(긴 영숫자 문자열). create_meeting 또는 search_online_meetings 작업에서 얻을 수 있습니다. 숫자 joinMeetingId와 다릅니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/get_team_members">
+    **설명:** 특정 팀의 멤버를 가져옵니다.
+
+    **매개변수:**
+    - `team_id` (string, 필수): 팀의 고유 식별자. get_teams 작업에서 얻을 수 있습니다.
+    - `top` (integer, 선택사항): 페이지당 검색할 멤버 수 (1-999). 기본값: 100.
+    - `skip_token` (string, 선택사항): 이전 응답의 페이지네이션 토큰. 응답에 @odata.nextLink가 포함된 경우 $skiptoken 매개변수 값을 추출하여 여기에 전달하면 다음 페이지 결과를 가져올 수 있습니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/create_channel">
+    **설명:** 팀에 새 채널을 만듭니다.
+
+    **매개변수:**
+    - `team_id` (string, 필수): 팀의 고유 식별자. get_teams 작업에서 얻을 수 있습니다.
+    - `display_name` (string, 필수): Teams에 표시되는 채널 이름. 팀 내에서 고유해야 합니다. 최대 50자.
+    - `description` (string, 선택사항): 채널 목적을 설명하는 선택적 설명. 채널 세부 정보에 표시됩니다. 최대 1024자.
+    - `membership_type` (string, 선택사항): 채널 가시성. 옵션: standard, private. "standard" = 모든 팀 멤버에게 표시, "private" = 명시적으로 추가된 멤버에게만 표시. 기본값: standard.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/get_message_replies">
+    **설명:** 채널의 특정 메시지에 대한 회신을 가져옵니다.
+
+    **매개변수:**
+    - `team_id` (string, 필수): 팀의 고유 식별자. get_teams 작업에서 얻을 수 있습니다.
+    - `channel_id` (string, 필수): 채널의 고유 식별자. get_channels 작업에서 얻을 수 있습니다.
+    - `message_id` (string, 필수): 상위 메시지의 고유 식별자. get_messages 작업에서 얻을 수 있습니다.
+    - `top` (integer, 선택사항): 페이지당 검색할 회신 수 (1-50). 기본값: 50.
+    - `skip_token` (string, 선택사항): 이전 응답의 페이지네이션 토큰. 응답에 @odata.nextLink가 포함된 경우 $skiptoken 매개변수 값을 추출하여 여기에 전달하면 다음 페이지 결과를 가져올 수 있습니다.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/reply_to_message">
+    **설명:** Teams 채널의 메시지에 회신합니다.
+
+    **매개변수:**
+    - `team_id` (string, 필수): 팀의 고유 식별자. get_teams 작업에서 얻을 수 있습니다.
+    - `channel_id` (string, 필수): 채널의 고유 식별자. get_channels 작업에서 얻을 수 있습니다.
+    - `message_id` (string, 필수): 회신할 메시지의 고유 식별자. get_messages 작업에서 얻을 수 있습니다.
+    - `message` (string, 필수): 회신 내용. HTML의 경우 서식 태그 포함. 텍스트의 경우 일반 텍스트만.
+    - `content_type` (string, 선택사항): 콘텐츠 형식. 옵션: html, text. "text"는 일반 텍스트, "html"은 서식이 있는 리치 텍스트. 기본값: text.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/update_meeting">
+    **설명:** 기존 온라인 회의를 업데이트합니다.
+
+    **매개변수:**
+    - `meeting_id` (string, 필수): 회의의 고유 식별자. create_meeting 또는 search_online_meetings 작업에서 얻을 수 있습니다.
+    - `subject` (string, 선택사항): 새 회의 제목.
+    - `startDateTime` (string, 선택사항): 시간대가 포함된 ISO 8601 형식의 새 시작 시간. 예: "2024-01-20T10:00:00-08:00".
+    - `endDateTime` (string, 선택사항): 시간대가 포함된 ISO 8601 형식의 새 종료 시간.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/delete_meeting">
+    **설명:** 온라인 회의를 삭제합니다.
+
+    **매개변수:**
+    - `meeting_id` (string, 필수): 삭제할 회의의 고유 식별자. create_meeting 또는 search_online_meetings 작업에서 얻을 수 있습니다.
+
+  </Accordion>
 </AccordionGroup>
 
 ## 사용 예제
@@ -140,6 +220,62 @@ crew = Crew(
 crew.kickoff()
 ```
 
+### 메시징 및 커뮤니케이션
+
+```python
+from crewai import Agent, Task, Crew
+
+# 메시징에 특화된 에이전트 생성
+messenger = Agent(
+    role="Teams 메신저",
+    goal="Teams 채널에서 메시지 전송 및 검색",
+    backstory="팀 커뮤니케이션 및 메시지 관리에 능숙한 AI 어시스턴트.",
+    apps=['microsoft_teams/send_message', 'microsoft_teams/get_messages']
+)
+
+# 메시지 전송 및 최근 메시지 검색 작업
+messaging_task = Task(
+    description="'your_team_id' 팀의 General 채널에 'Hello team! This is an automated update from our AI assistant.' 메시지를 보낸 다음 해당 채널의 최근 10개 메시지를 검색하세요.",
+    agent=messenger,
+    expected_output="메시지가 성공적으로 전송되고 최근 메시지가 검색됨."
+)
+
+crew = Crew(
+    agents=[messenger],
+    tasks=[messaging_task]
+)
+
+crew.kickoff()
+```
+
+### 회의 관리
+
+```python
+from crewai import Agent, Task, Crew
+
+# 회의 관리를 위한 에이전트 생성
+meeting_scheduler = Agent(
+    role="회의 스케줄러",
+    goal="Teams 회의 생성 및 관리",
+    backstory="회의 일정 관리 및 정리를 담당하는 AI 어시스턴트.",
+    apps=['microsoft_teams/create_meeting', 'microsoft_teams/search_online_meetings_by_join_url']
+)
+
+# 회의 생성 작업
+schedule_meeting_task = Task(
+    description="내일 오전 10시에 1시간 동안 진행되는 '주간 팀 동기화' 제목의 Teams 회의를 생성하세요 (시간대가 포함된 적절한 ISO 8601 형식 사용).",
+    agent=meeting_scheduler,
+    expected_output="회의 세부 정보와 함께 Teams 회의가 성공적으로 생성됨."
+)
+
+crew = Crew(
+    agents=[meeting_scheduler],
+    tasks=[schedule_meeting_task]
+)
+
+crew.kickoff()
+```
+
 ## 문제 해결
 
 ### 일반적인 문제
@@ -148,11 +284,35 @@ crew.kickoff()
 
 - Microsoft 계정이 Teams 액세스에 필요한 권한을 가지고 있는지 확인하세요.
 - 필요한 범위: `Team.ReadBasic.All`, `Channel.ReadBasic.All`, `ChannelMessage.Send`, `ChannelMessage.Read.All`, `OnlineMeetings.ReadWrite`, `OnlineMeetings.Read`.
+- OAuth 연결에 필요한 모든 범위가 포함되어 있는지 확인하세요.
 
 **팀 및 채널 액세스**
 
 - 액세스하려는 팀의 멤버인지 확인하세요.
 - 팀 및 채널 ID가 올바른지 다시 확인하세요.
+- 팀 및 채널 ID는 `get_teams` 및 `get_channels` 작업을 사용하여 얻을 수 있습니다.
+
+**메시지 전송 문제**
+
+- `send_message`에 `team_id`, `channel_id`, `message`가 제공되는지 확인하세요.
+- 지정된 채널에 메시지를 보낼 권한이 있는지 확인하세요.
+- 메시지 형식에 따라 적절한 `content_type`(text 또는 html)을 선택하세요.
+
+**회의 생성**
+
+- `subject`, `startDateTime`, `endDateTime`이 제공되는지 확인하세요.
+- 날짜/시간 필드에 시간대가 포함된 적절한 ISO 8601 형식을 사용하세요 (예: '2024-01-20T10:00:00-08:00').
+- 회의 시간이 미래인지 확인하세요.
+
+**메시지 검색 제한**
+
+- `get_messages` 작업은 요청당 최대 50개 메시지만 검색할 수 있습니다.
+- 메시지는 역시간순(최신순)으로 반환됩니다.
+
+**회의 검색**
+
+- `search_online_meetings_by_join_url`의 경우 참가 URL이 정확하고 올바르게 형식화되어 있는지 확인하세요.
+- URL은 완전한 Teams 회의 참가 URL이어야 합니다.
 
 ### 도움 받기
 

docs/ko/enterprise/integrations/microsoft_word.mdx

@@ -97,6 +97,26 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=your_enterprise_token
     - `file_id` (string, 필수): 삭제할 문서의 ID.
 
   </Accordion>
+
+  <Accordion title="microsoft_word/copy_document">
+    **설명:** OneDrive의 새 위치에 문서를 복사합니다.
+
+    **매개변수:**
+    - `file_id` (string, 필수): 복사할 문서의 ID.
+    - `name` (string, 선택사항): 복사된 문서의 새 이름.
+    - `parent_id` (string, 선택사항): 대상 폴더의 ID (기본값: 루트).
+
+  </Accordion>
+
+  <Accordion title="microsoft_word/move_document">
+    **설명:** OneDrive의 새 위치로 문서를 이동합니다.
+
+    **매개변수:**
+    - `file_id` (string, 필수): 이동할 문서의 ID.
+    - `parent_id` (string, 필수): 대상 폴더의 ID.
+    - `name` (string, 선택사항): 이동된 문서의 새 이름.
+
+  </Accordion>
 </AccordionGroup>
 
 ## 사용 예제

docs/ko/learn/human-feedback-in-flows.mdx

@@ -73,6 +73,8 @@ flow.kickoff()
 | `default_outcome` | `str` | 아니오 | 피드백이 제공되지 않을 때 사용할 outcome. `emit`에 있어야 합니다 |
 | `metadata` | `dict` | 아니오 | 엔터프라이즈 통합을 위한 추가 데이터 |
 | `provider` | `HumanFeedbackProvider` | 아니오 | 비동기/논블로킹 피드백을 위한 커스텀 프로바이더. [비동기 인간 피드백](#비동기-인간-피드백-논블로킹) 참조 |
+| `learn` | `bool` | 아니오 | HITL 학습 활성화: 피드백에서 교훈을 추출하고 향후 출력을 사전 검토합니다. 기본값 `False`. [피드백에서 학습하기](#피드백에서-학습하기) 참조 |
+| `learn_limit` | `int` | 아니오 | 사전 검토를 위해 불러올 최대 과거 교훈 수. 기본값 `5` |
 
 ### 기본 사용법 (라우팅 없음)
 
@@ -96,33 +98,43 @@ def handle_feedback(self, result):
 `emit`을 지정하면, 데코레이터는 라우터가 됩니다. 인간의 자유 형식 피드백이 LLM에 의해 해석되어 지정된 outcome 중 하나로 매핑됩니다:
 
 ```python Code
-@start()
-@human_feedback(
-    message="이 콘텐츠의 출판을 승인하시겠습니까?",
-    emit=["approved", "rejected", "needs_revision"],
-    llm="gpt-4o-mini",
-    default_outcome="needs_revision",
-)
-def review_content(self):
-    return "블로그 게시물 초안 내용..."
+from crewai.flow.flow import Flow, start, listen, or_
+from crewai.flow.human_feedback import human_feedback
 
-@listen("approved")
-def publish(self, result):
-    print(f"출판 중! 사용자 의견: {result.feedback}")
+class ReviewFlow(Flow):
+    @start()
+    def generate_content(self):
+        return "블로그 게시물 초안 내용..."
 
-@listen("rejected")
-def discard(self, result):
-    print(f"폐기됨. 이유: {result.feedback}")
+    @human_feedback(
+        message="이 콘텐츠의 출판을 승인하시겠습니까?",
+        emit=["approved", "rejected", "needs_revision"],
+        llm="gpt-4o-mini",
+        default_outcome="needs_revision",
+    )
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "블로그 게시물 초안 내용..."
 
-@listen("needs_revision")
-def revise(self, result):
-    print(f"다음을 기반으로 수정 중: {result.feedback}")
+    @listen("approved")
+    def publish(self, result):
+        print(f"출판 중! 사용자 의견: {result.feedback}")
+
+    @listen("rejected")
+    def discard(self, result):
+        print(f"폐기됨. 이유: {result.feedback}")
 ```
 
+사용자가 "더 자세한 내용이 필요합니다"와 같이 말하면, LLM이 이를 `"needs_revision"`으로 매핑하고, `or_()`를 통해 `review_content`가 다시 트리거됩니다 — 수정 루프가 생성됩니다. outcome이 `"approved"` 또는 `"rejected"`가 될 때까지 루프가 계속됩니다.
+
 <Tip>
 LLM은 가능한 경우 구조화된 출력(function calling)을 사용하여 응답이 지정된 outcome 중 하나임을 보장합니다. 이로 인해 라우팅이 신뢰할 수 있고 예측 가능해집니다.
 </Tip>
 
+<Warning>
+`@start()` 메서드는 flow 시작 시 한 번만 실행됩니다. 수정 루프가 필요한 경우, start 메서드를 review 메서드와 분리하고 review 메서드에 `@listen(or_("trigger", "revision_outcome"))`를 사용하여 self-loop을 활성화하세요.
+</Warning>
+
 ## HumanFeedbackResult
 
 `HumanFeedbackResult` 데이터클래스는 인간 피드백 상호작용에 대한 모든 정보를 포함합니다:
@@ -191,116 +203,162 @@ def summarize(self):
 <CodeGroup>
 
 ```python Code
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 from pydantic import BaseModel
 
 
 class ContentState(BaseModel):
-    topic: str = ""
     draft: str = ""
-    final_content: str = ""
     revision_count: int = 0
+    status: str = "pending"
 
 
 class ContentApprovalFlow(Flow[ContentState]):
-    """콘텐츠를 생성하고 인간의 승인을 받는 Flow입니다."""
+    """콘텐츠를 생성하고 승인될 때까지 반복하는 Flow."""
 
     @start()
-    def get_topic(self):
-        self.state.topic = input("어떤 주제에 대해 글을 쓸까요? ")
-        return self.state.topic
-
-    @listen(get_topic)
-    def generate_draft(self, topic):
-        # 실제 사용에서는 LLM을 호출합니다
-        self.state.draft = f"# {topic}\n\n{topic}에 대한 초안입니다..."
+    def generate_draft(self):
+        self.state.draft = "# AI 안전\n\nAI 안전에 대한 초안..."
         return self.state.draft
 
-    @listen(generate_draft)
     @human_feedback(
-        message="이 초안을 검토해 주세요. 'approved', 'rejected'로 답하거나 수정 피드백을 제공해 주세요:",
+        message="이 초안을 검토해 주세요. 승인, 거부 또는 변경이 필요한 사항을 설명해 주세요:",
         emit=["approved", "rejected", "needs_revision"],
         llm="gpt-4o-mini",
         default_outcome="needs_revision",
     )
-    def review_draft(self, draft):
-        return draft
+    @listen(or_("generate_draft", "needs_revision"))
+    def review_draft(self):
+        self.state.revision_count += 1
+        return f"{self.state.draft} (v{self.state.revision_count})"
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
-        self.state.final_content = result.output
-        print("\n✅ 콘텐츠가 승인되어 출판되었습니다!")
-        print(f"검토자 코멘트: {result.feedback}")
+        self.state.status = "published"
+        print(f"콘텐츠 승인 및 게시! 리뷰어 의견: {result.feedback}")
         return "published"
 
     @listen("rejected")
     def handle_rejection(self, result: HumanFeedbackResult):
-        print("\n❌ 콘텐츠가 거부되었습니다")
-        print(f"이유: {result.feedback}")
+        self.state.status = "rejected"
+        print(f"콘텐츠 거부됨. 이유: {result.feedback}")
         return "rejected"
 
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        self.state.revision_count += 1
-        print(f"\n📝 수정 #{self.state.revision_count} 요청됨")
-        print(f"피드백: {result.feedback}")
 
-        # 실제 Flow에서는 generate_draft로 돌아갈 수 있습니다
-        # 이 예제에서는 단순히 확인합니다
-        return "revision_requested"
-
-
-# Flow 실행
 flow = ContentApprovalFlow()
 result = flow.kickoff()
-print(f"\nFlow 완료. 요청된 수정: {flow.state.revision_count}")
+print(f"\nFlow 완료. 상태: {flow.state.status}, 검토 횟수: {flow.state.revision_count}")
 ```
 
 ```text Output
-어떤 주제에 대해 글을 쓸까요? AI 안전
+==================================================
+OUTPUT FOR REVIEW:
+==================================================
+# AI 안전
+
+AI 안전에 대한 초안... (v1)
+==================================================
+
+이 초안을 검토해 주세요. 승인, 거부 또는 변경이 필요한 사항을 설명해 주세요:
+(Press Enter to skip, or type your feedback)
+
+Your feedback: 더 자세한 내용이 필요합니다
 
 ==================================================
 OUTPUT FOR REVIEW:
 ==================================================
 # AI 안전
 
-AI 안전에 대한 초안입니다...
+AI 안전에 대한 초안... (v2)
 ==================================================
 
-이 초안을 검토해 주세요. 'approved', 'rejected'로 답하거나 수정 피드백을 제공해 주세요:
+이 초안을 검토해 주세요. 승인, 거부 또는 변경이 필요한 사항을 설명해 주세요:
 (Press Enter to skip, or type your feedback)
 
 Your feedback: 좋아 보입니다, 승인!
 
-✅ 콘텐츠가 승인되어 출판되었습니다!
-검토자 코멘트: 좋아 보입니다, 승인!
+콘텐츠 승인 및 게시! 리뷰어 의견: 좋아 보입니다, 승인!
 
-Flow 완료. 요청된 수정: 0
+Flow 완료. 상태: published, 검토 횟수: 2
 ```
 
 </CodeGroup>
 
 ## 다른 데코레이터와 결합하기
 
-`@human_feedback` 데코레이터는 다른 Flow 데코레이터와 함께 작동합니다. 가장 안쪽 데코레이터(함수에 가장 가까운)로 배치하세요:
+`@human_feedback` 데코레이터는 `@start()`, `@listen()`, `or_()`와 함께 작동합니다. 데코레이터 순서는 두 가지 모두 동작합니다—프레임워크가 양방향으로 속성을 전파합니다—하지만 권장 패턴은 다음과 같습니다:
 
 ```python Code
-# 올바름: @human_feedback이 가장 안쪽(함수에 가장 가까움)
+# Flow 시작 시 일회성 검토 (self-loop 없음)
 @start()
-@human_feedback(message="이것을 검토해 주세요:")
+@human_feedback(message="이것을 검토해 주세요:", emit=["approved", "rejected"], llm="gpt-4o-mini")
 def my_start_method(self):
     return "content"
 
+# 리스너에서 선형 검토 (self-loop 없음)
 @listen(other_method)
-@human_feedback(message="이것도 검토해 주세요:")
+@human_feedback(message="이것도 검토해 주세요:", emit=["good", "bad"], llm="gpt-4o-mini")
 def my_listener(self, data):
     return f"processed: {data}"
+
+# Self-loop: 수정을 위해 반복할 수 있는 검토
+@human_feedback(message="승인 또는 수정 요청?", emit=["approved", "revise"], llm="gpt-4o-mini")
+@listen(or_("upstream_method", "revise"))
+def review_with_loop(self):
+    return "content for review"
 ```
 
-<Tip>
-`@human_feedback`를 가장 안쪽 데코레이터(마지막/함수에 가장 가까움)로 배치하여 메서드를 직접 래핑하고 Flow 시스템에 전달하기 전에 반환 값을 캡처할 수 있도록 하세요.
-</Tip>
+### Self-loop 패턴
+
+수정 루프를 만들려면 `or_()`를 사용하여 검토 메서드가 **상위 트리거**와 **자체 수정 outcome**을 모두 리스닝해야 합니다:
+
+```python Code
+@start()
+def generate(self):
+    return "initial draft"
+
+@human_feedback(
+    message="승인하시겠습니까, 아니면 변경을 요청하시겠습니까?",
+    emit=["revise", "approved"],
+    llm="gpt-4o-mini",
+    default_outcome="approved",
+)
+@listen(or_("generate", "revise"))
+def review(self):
+    return "content"
+
+@listen("approved")
+def publish(self):
+    return "published"
+```
+
+outcome이 `"revise"`이면 flow가 `review`로 다시 라우팅됩니다 (`or_()`를 통해 `"revise"`를 리스닝하기 때문). outcome이 `"approved"`이면 flow가 `publish`로 계속됩니다. flow 엔진이 라우터를 "한 번만 실행" 규칙에서 제외하여 각 루프 반복마다 재실행할 수 있기 때문에 이 패턴이 동작합니다.
+
+### 체인된 라우터
+
+한 라우터의 outcome으로 트리거된 리스너가 그 자체로 라우터가 될 수 있습니다:
+
+```python Code
+@start()
+@human_feedback(message="첫 번째 검토:", emit=["approved", "rejected"], llm="gpt-4o-mini")
+def draft(self):
+    return "draft content"
+
+@listen("approved")
+@human_feedback(message="최종 검토:", emit=["publish", "revise"], llm="gpt-4o-mini")
+def final_review(self, prev):
+    return "final content"
+
+@listen("publish")
+def on_publish(self, prev):
+    return "published"
+```
+
+### 제한 사항
+
+- **`@start()` 메서드는 한 번만 실행**: `@start()` 메서드는 self-loop할 수 없습니다. 수정 주기가 필요하면 별도의 `@start()` 메서드를 진입점으로 사용하고 `@listen()` 메서드에 `@human_feedback`를 배치하세요.
+- **동일 메서드에 `@start()` + `@listen()` 불가**: 이는 Flow 프레임워크 제약입니다. 메서드는 시작점이거나 리스너여야 하며, 둘 다일 수 없습니다.
 
 ## 모범 사례
 
@@ -514,9 +572,9 @@ class ContentPipeline(Flow):
     @start()
     @human_feedback(
         message="이 콘텐츠의 출판을 승인하시겠습니까?",
-        emit=["approved", "rejected", "needs_revision"],
+        emit=["approved", "rejected"],
         llm="gpt-4o-mini",
-        default_outcome="needs_revision",
+        default_outcome="rejected",
         provider=SlackNotificationProvider("#content-reviews"),
     )
     def generate_content(self):
@@ -532,11 +590,6 @@ class ContentPipeline(Flow):
         print(f"보관됨. 이유: {result.feedback}")
         return {"status": "archived"}
 
-    @listen("needs_revision")
-    def queue_revision(self, result):
-        print(f"수정 대기열에 추가됨: {result.feedback}")
-        return {"status": "revision_needed"}
-
 
 # Flow 시작 (Slack 응답을 기다리며 일시 중지)
 def start_content_pipeline():
@@ -576,6 +629,64 @@ async def on_slack_feedback_async(flow_id: str, slack_message: str):
 5. **자동 영속성**: `HumanFeedbackPending`이 발생하면 상태가 자동으로 저장되며 기본적으로 `SQLiteFlowPersistence` 사용
 6. **커스텀 영속성**: 필요한 경우 `from_pending()`에 커스텀 영속성 인스턴스 전달
 
+## 피드백에서 학습하기
+
+`learn=True` 매개변수는 인간 검토자와 메모리 시스템 간의 피드백 루프를 활성화합니다. 활성화되면 시스템은 과거 인간의 수정 사항에서 학습하여 출력을 점진적으로 개선합니다.
+
+### 작동 방식
+
+1. **피드백 후**: LLM이 출력 + 피드백에서 일반화 가능한 교훈을 추출하고 `source="hitl"`로 메모리에 저장합니다. 피드백이 단순한 승인(예: "좋아 보입니다")인 경우 아무것도 저장하지 않습니다.
+2. **다음 검토 전**: 과거 HITL 교훈을 메모리에서 불러와 LLM이 인간이 보기 전에 출력을 개선하는 데 적용합니다.
+
+시간이 지남에 따라 각 수정 사항이 향후 검토에 반영되므로 인간은 점진적으로 더 나은 사전 검토된 출력을 보게 됩니다.
+
+### 예제
+
+```python Code
+class ArticleReviewFlow(Flow):
+    @start()
+    def generate_article(self):
+        return self.crew.kickoff(inputs={"topic": "AI Safety"}).raw
+
+    @human_feedback(
+        message="이 글 초안을 검토해 주세요:",
+        emit=["approved", "needs_revision"],
+        llm="gpt-4o-mini",
+        learn=True,
+    )
+    @listen(or_("generate_article", "needs_revision"))
+    def review_article(self):
+        return self.last_human_feedback.output if self.last_human_feedback else "article draft"
+
+    @listen("approved")
+    def publish(self):
+        print(f"Publishing: {self.last_human_feedback.output}")
+```
+
+**첫 번째 실행**: 인간이 원시 출력을 보고 "사실에 대한 주장에는 항상 인용을 포함하세요."라고 말합니다. 교훈이 추출되어 메모리에 저장됩니다.
+
+**두 번째 실행**: 시스템이 인용 교훈을 불러와 출력을 사전 검토하여 인용을 추가한 후 개선된 버전을 표시합니다. 인간의 역할이 "모든 것을 수정"에서 "시스템이 놓친 것을 찾기"로 전환됩니다.
+
+### 구성
+
+| 매개변수 | 기본값 | 설명 |
+|-----------|--------|------|
+| `learn` | `False` | HITL 학습 활성화 |
+| `learn_limit` | `5` | 사전 검토를 위해 불러올 최대 과거 교훈 수 |
+
+### 주요 설계 결정
+
+- **모든 것에 동일한 LLM 사용**: 데코레이터의 `llm` 매개변수는 outcome 매핑, 교훈 추출, 사전 검토에 공유됩니다. 여러 모델을 구성할 필요가 없습니다.
+- **구조화된 출력**: 추출과 사전 검토 모두 LLM이 지원하는 경우 Pydantic 모델과 함께 function calling을 사용하고, 그렇지 않으면 텍스트 파싱으로 폴백합니다.
+- **논블로킹 저장**: 교훈은 백그라운드 스레드에서 실행되는 `remember_many()`를 통해 저장됩니다 -- Flow는 즉시 계속됩니다.
+- **우아한 저하**: 추출 중 LLM이 실패하면 아무것도 저장하지 않습니다. 사전 검토 중 실패하면 원시 출력이 표시됩니다. 어느 쪽의 실패도 Flow를 차단하지 않습니다.
+- **범위/카테고리 불필요**: 교훈을 저장할 때 `source`만 전달됩니다. 인코딩 파이프라인이 범위, 카테고리, 중요도를 자동으로 추론합니다.
+
+<Note>
+`learn=True`는 Flow에 메모리가 사용 가능해야 합니다. Flow는 기본적으로 자동으로 메모리를 얻지만, `_skip_auto_memory`로 비활성화한 경우 HITL 학습은 조용히 건너뜁니다.
+</Note>
+
+
 ## 관련 문서
 
 - [Flow 개요](/ko/concepts/flows) - CrewAI Flow에 대해 알아보기
@@ -583,3 +694,4 @@ async def on_slack_feedback_async(flow_id: str, slack_message: str):
 - [Flow 영속성](/ko/concepts/flows#persistence) - Flow 상태 영속화
 - [@router를 사용한 라우팅](/ko/concepts/flows#router) - 조건부 라우팅에 대해 더 알아보기
 - [실행 시 인간 입력](/ko/learn/human-input-on-execution) - 태스크 수준 인간 입력
+- [메모리](/ko/concepts/memory) - HITL 학습에서 사용되는 통합 메모리 시스템

docs/pt-BR/enterprise/features/flow-hitl-management.mdx

@@ -38,22 +38,21 @@ O CrewAI Enterprise oferece um sistema abrangente de gerenciamento Human-in-the-
 Configure checkpoints de revisão humana em seus Flows usando o decorador `@human_feedback`. Quando a execução atinge um ponto de revisão, o sistema pausa, notifica o responsável via email e aguarda uma resposta.
 
 ```python
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 
 class ContentApprovalFlow(Flow):
     @start()
     def generate_content(self):
-        # IA gera conteúdo
         return "Texto de marketing gerado para campanha Q1..."
 
-    @listen(generate_content)
     @human_feedback(
         message="Por favor, revise este conteúdo para conformidade com a marca:",
         emit=["approved", "rejected", "needs_revision"],
     )
-    def review_content(self, content):
-        return content
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "Texto de marketing para revisão..."
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
@@ -62,10 +61,6 @@ class ContentApprovalFlow(Flow):
     @listen("rejected")
     def archive_content(self, result: HumanFeedbackResult):
         print(f"Conteúdo rejeitado. Motivo: {result.feedback}")
-
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        print(f"Revisão solicitada: {result.feedback}")
 ```
 
 Para detalhes completos de implementação, consulte o guia [Feedback Humano em Flows](/pt-BR/learn/human-feedback-in-flows).

docs/pt-BR/enterprise/integrations/google_contacts.mdx

@@ -200,6 +200,25 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
     - `clientData` (array, opcional): Dados específicos do cliente. Cada item é um objeto com `key` (string) e `value` (string).
 
   </Accordion>
+
+  <Accordion title="google_contacts/update_contact_group">
+    **Descrição:** Atualizar informações de um grupo de contatos.
+
+    **Parâmetros:**
+    - `resourceName` (string, obrigatório): O nome do recurso do grupo de contatos (ex: 'contactGroups/myContactGroup').
+    - `name` (string, obrigatório): O nome do grupo de contatos.
+    - `clientData` (array, opcional): Dados específicos do cliente. Cada item é um objeto com `key` (string) e `value` (string).
+
+  </Accordion>
+
+  <Accordion title="google_contacts/delete_contact_group">
+    **Descrição:** Excluir um grupo de contatos.
+
+    **Parâmetros:**
+    - `resourceName` (string, obrigatório): O nome do recurso do grupo de contatos a excluir (ex: 'contactGroups/myContactGroup').
+    - `deleteContacts` (boolean, opcional): Se os contatos do grupo também devem ser excluídos. Padrão: false
+
+  </Accordion>
 </AccordionGroup>
 
 ## Exemplos de Uso

docs/pt-BR/enterprise/integrations/google_docs.mdx

@@ -131,6 +131,297 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
     - `endIndex` (integer, obrigatório): O índice final do intervalo.
 
   </Accordion>
+
+  <Accordion title="google_docs/create_document_with_content">
+    **Descrição:** Criar um novo documento do Google com conteúdo em uma única ação.
+
+    **Parâmetros:**
+    - `title` (string, obrigatório): O título para o novo documento. Aparece no topo do documento e no Google Drive.
+    - `content` (string, opcional): O conteúdo de texto a inserir no documento. Use `\n` para novos parágrafos.
+
+  </Accordion>
+
+  <Accordion title="google_docs/append_text">
+    **Descrição:** Adicionar texto ao final de um documento do Google. Insere automaticamente no final do documento sem necessidade de especificar um índice.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento obtido da resposta de create_document ou URL.
+    - `text` (string, obrigatório): Texto a adicionar ao final do documento. Use `\n` para novos parágrafos.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_bold">
+    **Descrição:** Aplicar ou remover formatação de negrito em texto de um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do texto a formatar.
+    - `endIndex` (integer, obrigatório): Posição final do texto a formatar (exclusivo).
+    - `bold` (boolean, obrigatório): Defina `true` para aplicar negrito, `false` para remover negrito.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_italic">
+    **Descrição:** Aplicar ou remover formatação de itálico em texto de um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do texto a formatar.
+    - `endIndex` (integer, obrigatório): Posição final do texto a formatar (exclusivo).
+    - `italic` (boolean, obrigatório): Defina `true` para aplicar itálico, `false` para remover itálico.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_underline">
+    **Descrição:** Adicionar ou remover formatação de sublinhado em texto de um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do texto a formatar.
+    - `endIndex` (integer, obrigatório): Posição final do texto a formatar (exclusivo).
+    - `underline` (boolean, obrigatório): Defina `true` para sublinhar, `false` para remover sublinhado.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_strikethrough">
+    **Descrição:** Adicionar ou remover formatação de tachado em texto de um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do texto a formatar.
+    - `endIndex` (integer, obrigatório): Posição final do texto a formatar (exclusivo).
+    - `strikethrough` (boolean, obrigatório): Defina `true` para adicionar tachado, `false` para remover.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_font_size">
+    **Descrição:** Alterar o tamanho da fonte do texto em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do texto a formatar.
+    - `endIndex` (integer, obrigatório): Posição final do texto a formatar (exclusivo).
+    - `fontSize` (number, obrigatório): Tamanho da fonte em pontos. Tamanhos comuns: 10, 11, 12, 14, 16, 18, 24, 36.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_text_color">
+    **Descrição:** Alterar a cor do texto usando valores RGB (escala 0-1) em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do texto a formatar.
+    - `endIndex` (integer, obrigatório): Posição final do texto a formatar (exclusivo).
+    - `red` (number, obrigatório): Componente vermelho (0-1). Exemplo: `1` para vermelho total.
+    - `green` (number, obrigatório): Componente verde (0-1). Exemplo: `0.5` para metade verde.
+    - `blue` (number, obrigatório): Componente azul (0-1). Exemplo: `0` para sem azul.
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_hyperlink">
+    **Descrição:** Transformar texto existente em um hyperlink clicável em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do texto a transformar em link.
+    - `endIndex` (integer, obrigatório): Posição final do texto a transformar em link (exclusivo).
+    - `url` (string, obrigatório): A URL para a qual o link deve apontar. Exemplo: `"https://example.com"`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/apply_heading_style">
+    **Descrição:** Aplicar um estilo de título ou parágrafo a um intervalo de texto em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do(s) parágrafo(s) a estilizar.
+    - `endIndex` (integer, obrigatório): Posição final do(s) parágrafo(s) a estilizar.
+    - `style` (string, obrigatório): O estilo a aplicar. Opções: `NORMAL_TEXT`, `TITLE`, `SUBTITLE`, `HEADING_1`, `HEADING_2`, `HEADING_3`, `HEADING_4`, `HEADING_5`, `HEADING_6`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_paragraph_alignment">
+    **Descrição:** Definir o alinhamento de texto para parágrafos em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do(s) parágrafo(s) a alinhar.
+    - `endIndex` (integer, obrigatório): Posição final do(s) parágrafo(s) a alinhar.
+    - `alignment` (string, obrigatório): Alinhamento do texto. Opções: `START` (esquerda), `CENTER`, `END` (direita), `JUSTIFIED`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/set_line_spacing">
+    **Descrição:** Definir o espaçamento entre linhas para parágrafos em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial do(s) parágrafo(s).
+    - `endIndex` (integer, obrigatório): Posição final do(s) parágrafo(s).
+    - `lineSpacing` (number, obrigatório): Espaçamento entre linhas como porcentagem. `100` = simples, `115` = 1.15x, `150` = 1.5x, `200` = duplo.
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_paragraph_bullets">
+    **Descrição:** Converter parágrafos em uma lista com marcadores ou numerada em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial dos parágrafos a converter em lista.
+    - `endIndex` (integer, obrigatório): Posição final dos parágrafos a converter em lista.
+    - `bulletPreset` (string, obrigatório): Estilo de marcadores/numeração. Opções: `BULLET_DISC_CIRCLE_SQUARE`, `BULLET_DIAMONDX_ARROW3D_SQUARE`, `BULLET_CHECKBOX`, `BULLET_ARROW_DIAMOND_DISC`, `BULLET_STAR_CIRCLE_SQUARE`, `NUMBERED_DECIMAL_ALPHA_ROMAN`, `NUMBERED_DECIMAL_ALPHA_ROMAN_PARENS`, `NUMBERED_DECIMAL_NESTED`, `NUMBERED_UPPERALPHA_ALPHA_ROMAN`, `NUMBERED_UPPERROMAN_UPPERALPHA_DECIMAL`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_paragraph_bullets">
+    **Descrição:** Remover marcadores ou numeração de parágrafos em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `startIndex` (integer, obrigatório): Posição inicial dos parágrafos de lista.
+    - `endIndex` (integer, obrigatório): Posição final dos parágrafos de lista.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_table_with_content">
+    **Descrição:** Inserir uma tabela com conteúdo em um documento do Google em uma única ação. Forneça o conteúdo como um array 2D.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `rows` (integer, obrigatório): Número de linhas na tabela.
+    - `columns` (integer, obrigatório): Número de colunas na tabela.
+    - `index` (integer, opcional): Posição para inserir a tabela. Se não fornecido, a tabela é inserida no final do documento.
+    - `content` (array, obrigatório): Conteúdo da tabela como um array 2D. Cada array interno é uma linha. Exemplo: `[["Ano", "Receita"], ["2023", "$43B"], ["2024", "$45B"]]`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_table_row">
+    **Descrição:** Inserir uma nova linha acima ou abaixo de uma célula de referência em uma tabela existente.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `tableStartIndex` (integer, obrigatório): O índice inicial da tabela. Obtenha de get_document.
+    - `rowIndex` (integer, obrigatório): Índice da linha (baseado em 0) da célula de referência.
+    - `columnIndex` (integer, opcional): Índice da coluna (baseado em 0) da célula de referência. Padrão: `0`.
+    - `insertBelow` (boolean, opcional): Se `true`, insere abaixo da linha de referência. Se `false`, insere acima. Padrão: `true`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_table_column">
+    **Descrição:** Inserir uma nova coluna à esquerda ou à direita de uma célula de referência em uma tabela existente.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `tableStartIndex` (integer, obrigatório): O índice inicial da tabela.
+    - `rowIndex` (integer, opcional): Índice da linha (baseado em 0) da célula de referência. Padrão: `0`.
+    - `columnIndex` (integer, obrigatório): Índice da coluna (baseado em 0) da célula de referência.
+    - `insertRight` (boolean, opcional): Se `true`, insere à direita. Se `false`, insere à esquerda. Padrão: `true`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_table_row">
+    **Descrição:** Excluir uma linha de uma tabela existente em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `tableStartIndex` (integer, obrigatório): O índice inicial da tabela.
+    - `rowIndex` (integer, obrigatório): Índice da linha (baseado em 0) a excluir.
+    - `columnIndex` (integer, opcional): Índice da coluna (baseado em 0) de qualquer célula na linha. Padrão: `0`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_table_column">
+    **Descrição:** Excluir uma coluna de uma tabela existente em um documento do Google.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `tableStartIndex` (integer, obrigatório): O índice inicial da tabela.
+    - `rowIndex` (integer, opcional): Índice da linha (baseado em 0) de qualquer célula na coluna. Padrão: `0`.
+    - `columnIndex` (integer, obrigatório): Índice da coluna (baseado em 0) a excluir.
+
+  </Accordion>
+
+  <Accordion title="google_docs/merge_table_cells">
+    **Descrição:** Mesclar um intervalo de células de tabela em uma única célula. O conteúdo de todas as células é preservado.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `tableStartIndex` (integer, obrigatório): O índice inicial da tabela.
+    - `rowIndex` (integer, obrigatório): Índice da linha inicial (baseado em 0) para a mesclagem.
+    - `columnIndex` (integer, obrigatório): Índice da coluna inicial (baseado em 0) para a mesclagem.
+    - `rowSpan` (integer, obrigatório): Número de linhas a mesclar.
+    - `columnSpan` (integer, obrigatório): Número de colunas a mesclar.
+
+  </Accordion>
+
+  <Accordion title="google_docs/unmerge_table_cells">
+    **Descrição:** Desfazer a mesclagem de células de tabela previamente mescladas, retornando-as a células individuais.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `tableStartIndex` (integer, obrigatório): O índice inicial da tabela.
+    - `rowIndex` (integer, obrigatório): Índice da linha (baseado em 0) da célula mesclada.
+    - `columnIndex` (integer, obrigatório): Índice da coluna (baseado em 0) da célula mesclada.
+    - `rowSpan` (integer, obrigatório): Número de linhas que a célula mesclada abrange.
+    - `columnSpan` (integer, obrigatório): Número de colunas que a célula mesclada abrange.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_inline_image">
+    **Descrição:** Inserir uma imagem de uma URL pública em um documento do Google. A imagem deve ser publicamente acessível, ter menos de 50MB e estar no formato PNG/JPEG/GIF.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `uri` (string, obrigatório): URL pública da imagem. Deve ser acessível sem autenticação.
+    - `index` (integer, opcional): Posição para inserir a imagem. Se não fornecido, a imagem é inserida no final do documento. Padrão: `1`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/insert_section_break">
+    **Descrição:** Inserir uma quebra de seção para criar seções de documento com formatação diferente.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `index` (integer, obrigatório): Posição para inserir a quebra de seção.
+    - `sectionType` (string, obrigatório): O tipo de quebra de seção. Opções: `CONTINUOUS` (permanece na mesma página), `NEXT_PAGE` (inicia uma nova página).
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_header">
+    **Descrição:** Criar um cabeçalho para o documento. Retorna um headerId que pode ser usado com insert_text para adicionar conteúdo ao cabeçalho.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `type` (string, opcional): Tipo de cabeçalho. Opções: `DEFAULT`. Padrão: `DEFAULT`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/create_footer">
+    **Descrição:** Criar um rodapé para o documento. Retorna um footerId que pode ser usado com insert_text para adicionar conteúdo ao rodapé.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `type` (string, opcional): Tipo de rodapé. Opções: `DEFAULT`. Padrão: `DEFAULT`.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_header">
+    **Descrição:** Excluir um cabeçalho do documento. Use get_document para encontrar o headerId.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `headerId` (string, obrigatório): O ID do cabeçalho a excluir. Obtenha da resposta de get_document.
+
+  </Accordion>
+
+  <Accordion title="google_docs/delete_footer">
+    **Descrição:** Excluir um rodapé do documento. Use get_document para encontrar o footerId.
+
+    **Parâmetros:**
+    - `documentId` (string, obrigatório): O ID do documento.
+    - `footerId` (string, obrigatório): O ID do rodapé a excluir. Obtenha da resposta de get_document.
+
+  </Accordion>
 </AccordionGroup>
 
 ## Exemplos de Uso

docs/pt-BR/enterprise/integrations/google_slides.mdx

@@ -61,6 +61,22 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
 
   </Accordion>
 
+  <Accordion title="google_slides/get_presentation_metadata">
+    **Descrição:** Obter metadados leves de uma apresentação (título, número de slides, IDs dos slides). Use isso primeiro antes de recuperar o conteúdo completo.
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação a ser recuperada.
+
+  </Accordion>
+
+  <Accordion title="google_slides/get_presentation_text">
+    **Descrição:** Extrair todo o conteúdo de texto de uma apresentação. Retorna IDs dos slides e texto de formas e tabelas apenas (sem formatação).
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+
+  </Accordion>
+
   <Accordion title="google_slides/get_presentation">
     **Descrição:** Recupera uma apresentação por ID.
 
@@ -80,6 +96,15 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
 
   </Accordion>
 
+  <Accordion title="google_slides/get_slide_text">
+    **Descrição:** Extrair conteúdo de texto de um único slide. Retorna apenas texto de formas e tabelas (sem formatação ou estilo).
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `pageObjectId` (string, obrigatório): O ID do slide/página para obter o texto.
+
+  </Accordion>
+
   <Accordion title="google_slides/get_page">
     **Descrição:** Recupera uma página específica por seu ID.
 
@@ -98,6 +123,120 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
 
   </Accordion>
 
+  <Accordion title="google_slides/create_slide">
+    **Descrição:** Adicionar um slide em branco adicional a uma apresentação. Novas apresentações já possuem um slide em branco - verifique get_presentation_metadata primeiro. Para slides com áreas de título/corpo, use create_slide_with_layout.
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `insertionIndex` (integer, opcional): Onde inserir o slide (baseado em 0). Se omitido, adiciona no final.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_slide_with_layout">
+    **Descrição:** Criar um slide com layout predefinido contendo áreas de espaço reservado para título, corpo, etc. Melhor que create_slide para conteúdo estruturado. Após criar, use get_page para encontrar os IDs de espaço reservado, depois insira texto neles.
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `layout` (string, obrigatório): Tipo de layout. Um de: `BLANK`, `TITLE`, `TITLE_AND_BODY`, `TITLE_AND_TWO_COLUMNS`, `TITLE_ONLY`, `SECTION_HEADER`, `ONE_COLUMN_TEXT`, `MAIN_POINT`, `BIG_NUMBER`. TITLE_AND_BODY é melhor para título+descrição. TITLE para slides apenas com título. SECTION_HEADER para divisores de seção.
+    - `insertionIndex` (integer, opcional): Onde inserir (baseado em 0). Se omitido, adiciona no final.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_text_box">
+    **Descrição:** Criar uma caixa de texto em um slide com conteúdo. Use para títulos, descrições, parágrafos - não para tabelas. Opcionalmente especifique posição (x, y) e tamanho (width, height) em unidades EMU (914400 EMU = 1 polegada).
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `slideId` (string, obrigatório): O ID do slide para adicionar a caixa de texto.
+    - `text` (string, obrigatório): O conteúdo de texto da caixa de texto.
+    - `x` (integer, opcional): Posição X em EMU (914400 = 1 polegada). Padrão: 914400 (1 polegada da esquerda).
+    - `y` (integer, opcional): Posição Y em EMU (914400 = 1 polegada). Padrão: 914400 (1 polegada do topo).
+    - `width` (integer, opcional): Largura em EMU. Padrão: 7315200 (~8 polegadas).
+    - `height` (integer, opcional): Altura em EMU. Padrão: 914400 (~1 polegada).
+
+  </Accordion>
+
+  <Accordion title="google_slides/delete_slide">
+    **Descrição:** Remover um slide de uma apresentação. Use get_presentation primeiro para encontrar o ID do slide.
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `slideId` (string, obrigatório): O ID do objeto do slide a excluir. Obtenha de get_presentation.
+
+  </Accordion>
+
+  <Accordion title="google_slides/duplicate_slide">
+    **Descrição:** Criar uma cópia de um slide existente. A duplicata é inserida imediatamente após o original.
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `slideId` (string, obrigatório): O ID do objeto do slide a duplicar. Obtenha de get_presentation.
+
+  </Accordion>
+
+  <Accordion title="google_slides/move_slides">
+    **Descrição:** Reordenar slides movendo-os para uma nova posição. Os IDs dos slides devem estar na ordem atual da apresentação (sem duplicatas).
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `slideIds` (array de strings, obrigatório): Array de IDs dos slides a mover. Obrigatoriamente na ordem atual da apresentação.
+    - `insertionIndex` (integer, obrigatório): Posição de destino (baseado em 0). 0 = início, número de slides = final.
+
+  </Accordion>
+
+  <Accordion title="google_slides/insert_youtube_video">
+    **Descrição:** Incorporar um vídeo do YouTube em um slide. O ID do vídeo é o valor após "v=" nas URLs do YouTube (ex: para youtube.com/watch?v=abc123, use "abc123").
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `slideId` (string, obrigatório): O ID do slide para adicionar o vídeo. Obtenha de get_presentation.
+    - `videoId` (string, obrigatório): O ID do vídeo do YouTube (o valor após v= na URL).
+
+  </Accordion>
+
+  <Accordion title="google_slides/insert_drive_video">
+    **Descrição:** Incorporar um vídeo do Google Drive em um slide. O ID do arquivo pode ser encontrado na URL do arquivo no Drive.
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `slideId` (string, obrigatório): O ID do slide para adicionar o vídeo. Obtenha de get_presentation.
+    - `fileId` (string, obrigatório): O ID do arquivo do Google Drive do vídeo.
+
+  </Accordion>
+
+  <Accordion title="google_slides/set_slide_background_image">
+    **Descrição:** Definir uma imagem de fundo para um slide. A URL da imagem deve ser publicamente acessível.
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `slideId` (string, obrigatório): O ID do slide para definir o fundo. Obtenha de get_presentation.
+    - `imageUrl` (string, obrigatório): URL publicamente acessível da imagem a usar como fundo.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_table">
+    **Descrição:** Criar uma tabela vazia em um slide. Para criar uma tabela com conteúdo, use create_table_with_content.
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `slideId` (string, obrigatório): O ID do slide para adicionar a tabela. Obtenha de get_presentation.
+    - `rows` (integer, obrigatório): Número de linhas na tabela.
+    - `columns` (integer, obrigatório): Número de colunas na tabela.
+
+  </Accordion>
+
+  <Accordion title="google_slides/create_table_with_content">
+    **Descrição:** Criar uma tabela com conteúdo em uma única ação. Forneça o conteúdo como uma matriz 2D onde cada array interno é uma linha. Exemplo: [["Cabeçalho1", "Cabeçalho2"], ["Linha1Col1", "Linha1Col2"]].
+
+    **Parâmetros:**
+    - `presentationId` (string, obrigatório): O ID da apresentação.
+    - `slideId` (string, obrigatório): O ID do slide para adicionar a tabela. Obtenha de get_presentation.
+    - `rows` (integer, obrigatório): Número de linhas na tabela.
+    - `columns` (integer, obrigatório): Número de colunas na tabela.
+    - `content` (array, obrigatório): Conteúdo da tabela como matriz 2D. Cada array interno é uma linha. Exemplo: [["Ano", "Receita"], ["2023", "$10M"]].
+
+  </Accordion>
+
   <Accordion title="google_slides/import_data_from_sheet">
     **Descrição:** Importa dados de uma planilha do Google para uma apresentação.
 

docs/pt-BR/enterprise/integrations/microsoft_excel.mdx

@@ -148,6 +148,16 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
 
   </Accordion>
 
+  <Accordion title="microsoft_excel/get_table_data">
+    **Descrição:** Obter dados de uma tabela específica em uma planilha do Excel.
+
+    **Parâmetros:**
+    - `file_id` (string, obrigatório): O ID do arquivo Excel.
+    - `worksheet_name` (string, obrigatório): Nome da planilha.
+    - `table_name` (string, obrigatório): Nome da tabela.
+
+  </Accordion>
+
   <Accordion title="microsoft_excel/create_chart">
     **Descrição:** Criar um gráfico em uma planilha do Excel.
 
@@ -180,6 +190,15 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
 
   </Accordion>
 
+  <Accordion title="microsoft_excel/get_used_range_metadata">
+    **Descrição:** Obter os metadados do intervalo usado (apenas dimensões, sem dados) de uma planilha do Excel.
+
+    **Parâmetros:**
+    - `file_id` (string, obrigatório): O ID do arquivo Excel.
+    - `worksheet_name` (string, obrigatório): Nome da planilha.
+
+  </Accordion>
+
   <Accordion title="microsoft_excel/list_charts">
     **Descrição:** Obter todos os gráficos em uma planilha do Excel.
 

docs/pt-BR/enterprise/integrations/microsoft_onedrive.mdx

@@ -150,6 +150,49 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
     - `item_id` (string, obrigatório): O ID do arquivo.
 
   </Accordion>
+
+  <Accordion title="microsoft_onedrive/list_files_by_path">
+    **Descrição:** Listar arquivos e pastas em um caminho específico do OneDrive.
+
+    **Parâmetros:**
+    - `folder_path` (string, obrigatório): O caminho da pasta (ex: 'Documents/Reports').
+    - `top` (integer, opcional): Número de itens a recuperar (máx 1000). Padrão: 50.
+    - `orderby` (string, opcional): Ordenar por campo (ex: "name asc", "lastModifiedDateTime desc"). Padrão: "name asc".
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/get_recent_files">
+    **Descrição:** Obter arquivos acessados recentemente no OneDrive.
+
+    **Parâmetros:**
+    - `top` (integer, opcional): Número de itens a recuperar (máx 200). Padrão: 25.
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/get_shared_with_me">
+    **Descrição:** Obter arquivos e pastas compartilhados com o usuário.
+
+    **Parâmetros:**
+    - `top` (integer, opcional): Número de itens a recuperar (máx 200). Padrão: 50.
+    - `orderby` (string, opcional): Ordenar por campo. Padrão: "name asc".
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/get_file_by_path">
+    **Descrição:** Obter informações sobre um arquivo ou pasta específica pelo caminho.
+
+    **Parâmetros:**
+    - `file_path` (string, obrigatório): O caminho do arquivo ou pasta (ex: 'Documents/report.docx').
+
+  </Accordion>
+
+  <Accordion title="microsoft_onedrive/download_file_by_path">
+    **Descrição:** Baixar um arquivo do OneDrive pelo seu caminho.
+
+    **Parâmetros:**
+    - `file_path` (string, obrigatório): O caminho do arquivo (ex: 'Documents/report.docx').
+
+  </Accordion>
 </AccordionGroup>
 
 ## Exemplos de Uso

docs/pt-BR/enterprise/integrations/microsoft_outlook.mdx

@@ -132,6 +132,74 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
     - `companyName` (string, opcional): Nome da empresa do contato.
 
   </Accordion>
+
+  <Accordion title="microsoft_outlook/get_message">
+    **Descrição:** Obter uma mensagem de email específica por ID.
+
+    **Parâmetros:**
+    - `message_id` (string, obrigatório): O identificador único da mensagem. Obter pela ação get_messages.
+    - `select` (string, opcional): Lista separada por vírgulas de propriedades a retornar. Exemplo: "id,subject,body,from,receivedDateTime". Padrão: "id,subject,body,from,toRecipients,receivedDateTime".
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/reply_to_email">
+    **Descrição:** Responder a uma mensagem de email.
+
+    **Parâmetros:**
+    - `message_id` (string, obrigatório): O identificador único da mensagem a responder. Obter pela ação get_messages.
+    - `comment` (string, obrigatório): O conteúdo da mensagem de resposta. Pode ser texto simples ou HTML. A mensagem original será citada abaixo deste conteúdo.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/forward_email">
+    **Descrição:** Encaminhar uma mensagem de email.
+
+    **Parâmetros:**
+    - `message_id` (string, obrigatório): O identificador único da mensagem a encaminhar. Obter pela ação get_messages.
+    - `to_recipients` (array, obrigatório): Array de endereços de email dos destinatários. Exemplo: ["john@example.com", "jane@example.com"].
+    - `comment` (string, opcional): Mensagem opcional a incluir acima do conteúdo encaminhado. Pode ser texto simples ou HTML.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/mark_message_read">
+    **Descrição:** Marcar uma mensagem como lida ou não lida.
+
+    **Parâmetros:**
+    - `message_id` (string, obrigatório): O identificador único da mensagem. Obter pela ação get_messages.
+    - `is_read` (boolean, obrigatório): Definir como true para marcar como lida, false para marcar como não lida.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/delete_message">
+    **Descrição:** Excluir uma mensagem de email.
+
+    **Parâmetros:**
+    - `message_id` (string, obrigatório): O identificador único da mensagem a excluir. Obter pela ação get_messages.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/update_event">
+    **Descrição:** Atualizar um evento de calendário existente.
+
+    **Parâmetros:**
+    - `event_id` (string, obrigatório): O identificador único do evento. Obter pela ação get_calendar_events.
+    - `subject` (string, opcional): Novo assunto/título do evento.
+    - `start_time` (string, opcional): Nova hora de início no formato ISO 8601 (ex: "2024-01-20T10:00:00"). OBRIGATÓRIO: Também deve fornecer start_timezone ao usar este campo.
+    - `start_timezone` (string, opcional): Fuso horário da hora de início. OBRIGATÓRIO ao atualizar start_time. Exemplos: "Pacific Standard Time", "Eastern Standard Time", "UTC".
+    - `end_time` (string, opcional): Nova hora de término no formato ISO 8601. OBRIGATÓRIO: Também deve fornecer end_timezone ao usar este campo.
+    - `end_timezone` (string, opcional): Fuso horário da hora de término. OBRIGATÓRIO ao atualizar end_time. Exemplos: "Pacific Standard Time", "Eastern Standard Time", "UTC".
+    - `location` (string, opcional): Novo local do evento.
+    - `body` (string, opcional): Novo corpo/descrição do evento. Suporta formatação HTML.
+
+  </Accordion>
+
+  <Accordion title="microsoft_outlook/delete_event">
+    **Descrição:** Excluir um evento de calendário.
+
+    **Parâmetros:**
+    - `event_id` (string, obrigatório): O identificador único do evento a excluir. Obter pela ação get_calendar_events.
+
+  </Accordion>
 </AccordionGroup>
 
 ## Exemplos de Uso

docs/pt-BR/enterprise/integrations/microsoft_sharepoint.mdx

@@ -77,6 +77,17 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
 
   </Accordion>
 
+  <Accordion title="microsoft_sharepoint/get_drives">
+    **Descrição:** Listar todas as bibliotecas de documentos (drives) em um site do SharePoint. Use isto para descobrir bibliotecas disponíveis antes de usar operações de arquivo.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `top` (integer, opcional): Número máximo de drives a retornar por página (1-999). Padrão: 100
+    - `skip_token` (string, opcional): Token de paginação de uma resposta anterior para buscar a próxima página de resultados.
+    - `select` (string, opcional): Lista de propriedades separadas por vírgula para retornar (ex: 'id,name,webUrl,driveType').
+
+  </Accordion>
+
   <Accordion title="microsoft_sharepoint/get_site_lists">
     **Descrição:** Obter todas as listas em um site do SharePoint.
 
@@ -145,20 +156,317 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
 
   </Accordion>
 
-  <Accordion title="microsoft_sharepoint/get_drive_items">
-    **Descrição:** Obter arquivos e pastas de uma biblioteca de documentos do SharePoint.
+  <Accordion title="microsoft_sharepoint/list_files">
+    **Descrição:** Recuperar arquivos e pastas de uma biblioteca de documentos do SharePoint. Por padrão, lista a pasta raiz, mas você pode navegar em subpastas fornecendo um folder_id.
 
     **Parâmetros:**
-    - `site_id` (string, obrigatório): O ID do site do SharePoint.
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `folder_id` (string, opcional): O ID da pasta para listar o conteúdo. Use 'root' para a pasta raiz, ou forneça um ID de pasta de uma chamada anterior de list_files. Padrão: 'root'
+    - `top` (integer, opcional): Número máximo de itens a retornar por página (1-1000). Padrão: 50
+    - `skip_token` (string, opcional): Token de paginação de uma resposta anterior para buscar a próxima página de resultados.
+    - `orderby` (string, opcional): Ordem de classificação dos resultados (ex: 'name asc', 'size desc', 'lastModifiedDateTime desc'). Padrão: 'name asc'
+    - `filter` (string, opcional): Filtro OData para restringir resultados (ex: 'file ne null' apenas para arquivos, 'folder ne null' apenas para pastas).
+    - `select` (string, opcional): Lista de campos separados por vírgula para retornar (ex: 'id,name,size,folder,file,webUrl,lastModifiedDateTime').
 
   </Accordion>
 
-  <Accordion title="microsoft_sharepoint/delete_drive_item">
-    **Descrição:** Excluir um arquivo ou pasta da biblioteca de documentos do SharePoint.
+  <Accordion title="microsoft_sharepoint/delete_file">
+    **Descrição:** Excluir um arquivo ou pasta de uma biblioteca de documentos do SharePoint. Para pastas, todo o conteúdo é excluído recursivamente. Os itens são movidos para a lixeira do site.
 
     **Parâmetros:**
-    - `site_id` (string, obrigatório): O ID do site do SharePoint.
-    - `item_id` (string, obrigatório): O ID do arquivo ou pasta a excluir.
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo ou pasta a excluir. Obtenha de list_files.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/list_files_by_path">
+    **Descrição:** Listar arquivos e pastas em uma pasta de biblioteca de documentos do SharePoint pelo caminho. Mais eficiente do que múltiplas chamadas list_files para navegação profunda.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `folder_path` (string, obrigatório): O caminho completo para a pasta sem barras iniciais/finais (ex: 'Documents', 'Reports/2024/Q1').
+    - `top` (integer, opcional): Número máximo de itens a retornar por página (1-1000). Padrão: 50
+    - `skip_token` (string, opcional): Token de paginação de uma resposta anterior para buscar a próxima página de resultados.
+    - `orderby` (string, opcional): Ordem de classificação dos resultados (ex: 'name asc', 'size desc'). Padrão: 'name asc'
+    - `select` (string, opcional): Lista de campos separados por vírgula para retornar (ex: 'id,name,size,folder,file,webUrl,lastModifiedDateTime').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/download_file">
+    **Descrição:** Baixar conteúdo bruto de um arquivo de uma biblioteca de documentos do SharePoint. Use apenas para arquivos de texto simples (.txt, .csv, .json). Para arquivos Excel, use as ações específicas de Excel. Para arquivos Word, use get_word_document_content.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo a baixar. Obtenha de list_files ou list_files_by_path.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_file_info">
+    **Descrição:** Recuperar metadados detalhados de um arquivo ou pasta específico em uma biblioteca de documentos do SharePoint, incluindo nome, tamanho, datas de criação/modificação e informações do autor.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo ou pasta. Obtenha de list_files ou list_files_by_path.
+    - `select` (string, opcional): Lista de propriedades separadas por vírgula para retornar (ex: 'id,name,size,createdDateTime,lastModifiedDateTime,webUrl,createdBy,lastModifiedBy').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/create_folder">
+    **Descrição:** Criar uma nova pasta em uma biblioteca de documentos do SharePoint. Por padrão, cria a pasta na raiz; use parent_id para criar subpastas.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `folder_name` (string, obrigatório): Nome para a nova pasta. Não pode conter: \ / : * ? " < > |
+    - `parent_id` (string, opcional): O ID da pasta pai. Use 'root' para a raiz da biblioteca de documentos, ou forneça um ID de pasta de list_files. Padrão: 'root'
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/search_files">
+    **Descrição:** Pesquisar arquivos e pastas em uma biblioteca de documentos do SharePoint por palavras-chave. Pesquisa nomes de arquivos, nomes de pastas e conteúdo de arquivos para documentos Office. Não use curingas ou caracteres especiais.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `query` (string, obrigatório): Palavras-chave de pesquisa (ex: 'relatório', 'orçamento 2024'). Curingas como *.txt não são suportados.
+    - `top` (integer, opcional): Número máximo de resultados a retornar por página (1-1000). Padrão: 50
+    - `skip_token` (string, opcional): Token de paginação de uma resposta anterior para buscar a próxima página de resultados.
+    - `select` (string, opcional): Lista de campos separados por vírgula para retornar (ex: 'id,name,size,folder,file,webUrl,lastModifiedDateTime').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/copy_file">
+    **Descrição:** Copiar um arquivo ou pasta para um novo local dentro do SharePoint. O item original permanece inalterado. A operação de cópia é assíncrona para arquivos grandes.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo ou pasta a copiar. Obtenha de list_files ou search_files.
+    - `destination_folder_id` (string, obrigatório): O ID da pasta de destino. Use 'root' para a pasta raiz, ou um ID de pasta de list_files.
+    - `new_name` (string, opcional): Novo nome para a cópia. Se não fornecido, o nome original é usado.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/move_file">
+    **Descrição:** Mover um arquivo ou pasta para um novo local dentro do SharePoint. O item é removido de sua localização original. Para pastas, todo o conteúdo é movido também.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo ou pasta a mover. Obtenha de list_files ou search_files.
+    - `destination_folder_id` (string, obrigatório): O ID da pasta de destino. Use 'root' para a pasta raiz, ou um ID de pasta de list_files.
+    - `new_name` (string, opcional): Novo nome para o item movido. Se não fornecido, o nome original é mantido.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_worksheets">
+    **Descrição:** Listar todas as planilhas (abas) em uma pasta de trabalho Excel armazenada em uma biblioteca de documentos do SharePoint. Use o nome da planilha retornado com outras ações de Excel.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `select` (string, opcional): Lista de propriedades separadas por vírgula para retornar (ex: 'id,name,position,visibility').
+    - `filter` (string, opcional): Expressão de filtro OData (ex: "visibility eq 'Visible'" para excluir planilhas ocultas).
+    - `top` (integer, opcional): Número máximo de planilhas a retornar. Mínimo: 1, Máximo: 999
+    - `orderby` (string, opcional): Ordem de classificação (ex: 'position asc' para retornar planilhas na ordem das abas).
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/create_excel_worksheet">
+    **Descrição:** Criar uma nova planilha (aba) em uma pasta de trabalho Excel armazenada em uma biblioteca de documentos do SharePoint. A nova planilha é adicionada no final da lista de abas.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `name` (string, obrigatório): Nome para a nova planilha. Máximo de 31 caracteres. Não pode conter: \ / * ? : [ ]. Deve ser único na pasta de trabalho.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_range_data">
+    **Descrição:** Recuperar valores de células de um intervalo específico em uma planilha Excel armazenada no SharePoint. Para ler todos os dados sem saber as dimensões, use get_excel_used_range em vez disso.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha (aba) para leitura. Obtenha de get_excel_worksheets. Sensível a maiúsculas e minúsculas.
+    - `range` (string, obrigatório): Intervalo de células em notação A1 (ex: 'A1:C10', 'A:C', '1:5', 'A1').
+    - `select` (string, opcional): Lista de propriedades separadas por vírgula para retornar (ex: 'address,values,formulas,numberFormat,text').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/update_excel_range_data">
+    **Descrição:** Escrever valores em um intervalo específico em uma planilha Excel armazenada no SharePoint. Sobrescreve o conteúdo existente das células. As dimensões do array de valores devem corresponder exatamente às dimensões do intervalo.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha (aba) a atualizar. Obtenha de get_excel_worksheets. Sensível a maiúsculas e minúsculas.
+    - `range` (string, obrigatório): Intervalo de células em notação A1 onde os valores serão escritos (ex: 'A1:C3' para um bloco 3x3).
+    - `values` (array, obrigatório): Array 2D de valores (linhas contendo células). Exemplo para A1:B2: [["Cabeçalho1", "Cabeçalho2"], ["Valor1", "Valor2"]]. Use null para limpar uma célula.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_used_range_metadata">
+    **Descrição:** Retornar apenas os metadados (endereço e dimensões) do intervalo utilizado em uma planilha, sem os valores reais das células. Ideal para arquivos grandes para entender o tamanho da planilha antes de ler dados em blocos.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha (aba) para leitura. Obtenha de get_excel_worksheets. Sensível a maiúsculas e minúsculas.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_used_range">
+    **Descrição:** Recuperar todas as células contendo dados em uma planilha armazenada no SharePoint. Não use para arquivos maiores que 2MB. Para arquivos grandes, use get_excel_used_range_metadata primeiro, depois get_excel_range_data para ler em blocos menores.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha (aba) para leitura. Obtenha de get_excel_worksheets. Sensível a maiúsculas e minúsculas.
+    - `select` (string, opcional): Lista de propriedades separadas por vírgula para retornar (ex: 'address,values,formulas,numberFormat,text,rowCount,columnCount').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_cell">
+    **Descrição:** Recuperar o valor de uma única célula por índice de linha e coluna de um arquivo Excel no SharePoint. Os índices são baseados em 0 (linha 0 = linha 1 do Excel, coluna 0 = coluna A).
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha (aba). Obtenha de get_excel_worksheets. Sensível a maiúsculas e minúsculas.
+    - `row` (integer, obrigatório): Índice de linha baseado em 0 (linha 0 = linha 1 do Excel). Intervalo válido: 0-1048575
+    - `column` (integer, obrigatório): Índice de coluna baseado em 0 (coluna 0 = A, coluna 1 = B). Intervalo válido: 0-16383
+    - `select` (string, opcional): Lista de propriedades separadas por vírgula para retornar (ex: 'address,values,formulas,numberFormat,text').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/add_excel_table">
+    **Descrição:** Converter um intervalo de células em uma tabela Excel formatada com recursos de filtragem, classificação e dados estruturados. Tabelas habilitam add_excel_table_row para adicionar dados.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha contendo o intervalo de dados. Obtenha de get_excel_worksheets.
+    - `range` (string, obrigatório): Intervalo de células para converter em tabela, incluindo cabeçalhos e dados (ex: 'A1:D10' onde A1:D1 contém cabeçalhos de coluna).
+    - `has_headers` (boolean, opcional): Defina como true se a primeira linha contém cabeçalhos de coluna. Padrão: true
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_tables">
+    **Descrição:** Listar todas as tabelas em uma planilha Excel específica armazenada no SharePoint. Retorna propriedades da tabela incluindo id, name, showHeaders e showTotals.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha para obter tabelas. Obtenha de get_excel_worksheets.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/add_excel_table_row">
+    **Descrição:** Adicionar uma nova linha ao final de uma tabela Excel em um arquivo do SharePoint. O array de valores deve ter o mesmo número de elementos que o número de colunas da tabela.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha contendo a tabela. Obtenha de get_excel_worksheets.
+    - `table_name` (string, obrigatório): Nome da tabela para adicionar a linha (ex: 'Table1'). Obtenha de get_excel_tables. Sensível a maiúsculas e minúsculas.
+    - `values` (array, obrigatório): Array de valores de células para a nova linha, um por coluna na ordem da tabela (ex: ["João Silva", "joao@exemplo.com", 25]).
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_excel_table_data">
+    **Descrição:** Obter todas as linhas de uma tabela Excel em um arquivo do SharePoint como um intervalo de dados. Mais fácil do que get_excel_range_data ao trabalhar com tabelas estruturadas, pois não é necessário saber o intervalo exato.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha contendo a tabela. Obtenha de get_excel_worksheets.
+    - `table_name` (string, obrigatório): Nome da tabela para obter dados (ex: 'Table1'). Obtenha de get_excel_tables. Sensível a maiúsculas e minúsculas.
+    - `select` (string, opcional): Lista de propriedades separadas por vírgula para retornar (ex: 'address,values,formulas,numberFormat,text').
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/create_excel_chart">
+    **Descrição:** Criar uma visualização de gráfico em uma planilha Excel armazenada no SharePoint a partir de um intervalo de dados. O gráfico é incorporado na planilha.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha onde o gráfico será criado. Obtenha de get_excel_worksheets.
+    - `chart_type` (string, obrigatório): Tipo de gráfico (ex: 'ColumnClustered', 'ColumnStacked', 'Line', 'LineMarkers', 'Pie', 'Bar', 'BarClustered', 'Area', 'Scatter', 'Doughnut').
+    - `source_data` (string, obrigatório): Intervalo de dados para o gráfico em notação A1, incluindo cabeçalhos (ex: 'A1:B10').
+    - `series_by` (string, opcional): Como as séries de dados são organizadas: 'Auto', 'Columns' ou 'Rows'. Padrão: 'Auto'
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/list_excel_charts">
+    **Descrição:** Listar todos os gráficos incorporados em uma planilha Excel armazenada no SharePoint. Retorna propriedades do gráfico incluindo id, name, chartType, height, width e position.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha para listar gráficos. Obtenha de get_excel_worksheets.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/delete_excel_worksheet">
+    **Descrição:** Remover permanentemente uma planilha (aba) e todo seu conteúdo de uma pasta de trabalho Excel armazenada no SharePoint. Não pode ser desfeito. Uma pasta de trabalho deve ter pelo menos uma planilha.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha a excluir. Sensível a maiúsculas e minúsculas. Todos os dados, tabelas e gráficos nesta planilha serão permanentemente removidos.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/delete_excel_table">
+    **Descrição:** Remover uma tabela de uma planilha Excel no SharePoint. Isto exclui a estrutura da tabela (filtragem, formatação, recursos de tabela) mas preserva os dados subjacentes das células.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+    - `worksheet_name` (string, obrigatório): Nome da planilha contendo a tabela. Obtenha de get_excel_worksheets.
+    - `table_name` (string, obrigatório): Nome da tabela a excluir (ex: 'Table1'). Obtenha de get_excel_tables. Os dados nas células permanecerão após a exclusão da tabela.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/list_excel_names">
+    **Descrição:** Recuperar todos os intervalos nomeados definidos em uma pasta de trabalho Excel armazenada no SharePoint. Intervalos nomeados são rótulos definidos pelo usuário para intervalos de células (ex: 'DadosVendas' para A1:D100).
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do arquivo Excel no SharePoint. Obtenha de list_files ou search_files.
+
+  </Accordion>
+
+  <Accordion title="microsoft_sharepoint/get_word_document_content">
+    **Descrição:** Baixar e extrair conteúdo de texto de um documento Word (.docx) armazenado em uma biblioteca de documentos do SharePoint. Esta é a maneira recomendada de ler documentos Word do SharePoint.
+
+    **Parâmetros:**
+    - `site_id` (string, obrigatório): O identificador completo do site SharePoint obtido de get_sites.
+    - `drive_id` (string, obrigatório): O ID da biblioteca de documentos. Chame get_drives primeiro para obter IDs de drive válidos.
+    - `item_id` (string, obrigatório): O identificador único do documento Word (.docx) no SharePoint. Obtenha de list_files ou search_files.
 
   </Accordion>
 </AccordionGroup>

docs/pt-BR/enterprise/integrations/microsoft_teams.mdx

@@ -107,6 +107,86 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
     - `join_web_url` (string, obrigatório): A URL de participação na web da reunião a pesquisar.
 
   </Accordion>
+
+  <Accordion title="microsoft_teams/search_online_meetings_by_meeting_id">
+    **Descrição:** Pesquisar reuniões online por ID externo da reunião.
+
+    **Parâmetros:**
+    - `join_meeting_id` (string, obrigatório): O ID da reunião (código numérico) que os participantes usam para entrar. É o joinMeetingId exibido nos convites da reunião, não o meeting id da API Graph.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/get_meeting">
+    **Descrição:** Obter detalhes de uma reunião online específica.
+
+    **Parâmetros:**
+    - `meeting_id` (string, obrigatório): O ID da reunião na API Graph (string alfanumérica longa). Obter pelas ações create_meeting ou search_online_meetings. Diferente do joinMeetingId numérico.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/get_team_members">
+    **Descrição:** Obter membros de uma equipe específica.
+
+    **Parâmetros:**
+    - `team_id` (string, obrigatório): O identificador único da equipe. Obter pela ação get_teams.
+    - `top` (integer, opcional): Número máximo de membros a recuperar por página (1-999). Padrão: 100.
+    - `skip_token` (string, opcional): Token de paginação de uma resposta anterior. Quando a resposta incluir @odata.nextLink, extraia o valor do parâmetro $skiptoken e passe aqui para obter a próxima página de resultados.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/create_channel">
+    **Descrição:** Criar um novo canal em uma equipe.
+
+    **Parâmetros:**
+    - `team_id` (string, obrigatório): O identificador único da equipe. Obter pela ação get_teams.
+    - `display_name` (string, obrigatório): Nome do canal exibido no Teams. Deve ser único na equipe. Máx 50 caracteres.
+    - `description` (string, opcional): Descrição opcional explicando o propósito do canal. Visível nos detalhes do canal. Máx 1024 caracteres.
+    - `membership_type` (string, opcional): Visibilidade do canal. Opções: standard, private. "standard" = visível para todos os membros da equipe, "private" = visível apenas para membros adicionados especificamente. Padrão: standard.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/get_message_replies">
+    **Descrição:** Obter respostas a uma mensagem específica em um canal.
+
+    **Parâmetros:**
+    - `team_id` (string, obrigatório): O identificador único da equipe. Obter pela ação get_teams.
+    - `channel_id` (string, obrigatório): O identificador único do canal. Obter pela ação get_channels.
+    - `message_id` (string, obrigatório): O identificador único da mensagem pai. Obter pela ação get_messages.
+    - `top` (integer, opcional): Número máximo de respostas a recuperar por página (1-50). Padrão: 50.
+    - `skip_token` (string, opcional): Token de paginação de uma resposta anterior. Quando a resposta incluir @odata.nextLink, extraia o valor do parâmetro $skiptoken e passe aqui para obter a próxima página de resultados.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/reply_to_message">
+    **Descrição:** Responder a uma mensagem em um canal do Teams.
+
+    **Parâmetros:**
+    - `team_id` (string, obrigatório): O identificador único da equipe. Obter pela ação get_teams.
+    - `channel_id` (string, obrigatório): O identificador único do canal. Obter pela ação get_channels.
+    - `message_id` (string, obrigatório): O identificador único da mensagem a responder. Obter pela ação get_messages.
+    - `message` (string, obrigatório): O conteúdo da resposta. Para HTML, inclua tags de formatação. Para texto, use apenas texto simples.
+    - `content_type` (string, opcional): Formato do conteúdo. Opções: html, text. "text" para texto simples, "html" para texto rico com formatação. Padrão: text.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/update_meeting">
+    **Descrição:** Atualizar uma reunião online existente.
+
+    **Parâmetros:**
+    - `meeting_id` (string, obrigatório): O identificador único da reunião. Obter pelas ações create_meeting ou search_online_meetings.
+    - `subject` (string, opcional): Novo título da reunião.
+    - `startDateTime` (string, opcional): Nova hora de início no formato ISO 8601 com fuso horário. Exemplo: "2024-01-20T10:00:00-08:00".
+    - `endDateTime` (string, opcional): Nova hora de término no formato ISO 8601 com fuso horário.
+
+  </Accordion>
+
+  <Accordion title="microsoft_teams/delete_meeting">
+    **Descrição:** Excluir uma reunião online.
+
+    **Parâmetros:**
+    - `meeting_id` (string, obrigatório): O identificador único da reunião a excluir. Obter pelas ações create_meeting ou search_online_meetings.
+
+  </Accordion>
 </AccordionGroup>
 
 ## Exemplos de Uso

docs/pt-BR/enterprise/integrations/microsoft_word.mdx

@@ -97,6 +97,26 @@ CREWAI_PLATFORM_INTEGRATION_TOKEN=seu_enterprise_token
     - `file_id` (string, obrigatório): O ID do documento a excluir.
 
   </Accordion>
+
+  <Accordion title="microsoft_word/copy_document">
+    **Descrição:** Copiar um documento para um novo local no OneDrive.
+
+    **Parâmetros:**
+    - `file_id` (string, obrigatório): O ID do documento a copiar.
+    - `name` (string, opcional): Novo nome para o documento copiado.
+    - `parent_id` (string, opcional): O ID da pasta de destino (padrão: raiz).
+
+  </Accordion>
+
+  <Accordion title="microsoft_word/move_document">
+    **Descrição:** Mover um documento para um novo local no OneDrive.
+
+    **Parâmetros:**
+    - `file_id` (string, obrigatório): O ID do documento a mover.
+    - `parent_id` (string, obrigatório): O ID da pasta de destino.
+    - `name` (string, opcional): Novo nome para o documento movido.
+
+  </Accordion>
 </AccordionGroup>
 
 ## Exemplos de Uso

docs/pt-BR/learn/human-feedback-in-flows.mdx

@@ -73,6 +73,8 @@ Quando este flow é executado, ele irá:
 | `default_outcome` | `str` | Não | Outcome a usar se nenhum feedback for fornecido. Deve estar em `emit` |
 | `metadata` | `dict` | Não | Dados adicionais para integrações enterprise |
 | `provider` | `HumanFeedbackProvider` | Não | Provider customizado para feedback assíncrono/não-bloqueante. Veja [Feedback Humano Assíncrono](#feedback-humano-assíncrono-não-bloqueante) |
+| `learn` | `bool` | Não | Habilitar aprendizado HITL: destila lições do feedback e pré-revisa saídas futuras. Padrão `False`. Veja [Aprendendo com Feedback](#aprendendo-com-feedback) |
+| `learn_limit` | `int` | Não | Máximo de lições passadas para recuperar na pré-revisão. Padrão `5` |
 
 ### Uso Básico (Sem Roteamento)
 
@@ -96,33 +98,43 @@ def handle_feedback(self, result):
 Quando você especifica `emit`, o decorador se torna um roteador. O feedback livre do humano é interpretado por um LLM e mapeado para um dos outcomes especificados:
 
 ```python Code
-@start()
-@human_feedback(
-    message="Você aprova este conteúdo para publicação?",
-    emit=["approved", "rejected", "needs_revision"],
-    llm="gpt-4o-mini",
-    default_outcome="needs_revision",
-)
-def review_content(self):
-    return "Rascunho do post do blog aqui..."
+from crewai.flow.flow import Flow, start, listen, or_
+from crewai.flow.human_feedback import human_feedback
 
-@listen("approved")
-def publish(self, result):
-    print(f"Publicando! Usuário disse: {result.feedback}")
+class ReviewFlow(Flow):
+    @start()
+    def generate_content(self):
+        return "Rascunho do post do blog aqui..."
 
-@listen("rejected")
-def discard(self, result):
-    print(f"Descartando. Motivo: {result.feedback}")
+    @human_feedback(
+        message="Você aprova este conteúdo para publicação?",
+        emit=["approved", "rejected", "needs_revision"],
+        llm="gpt-4o-mini",
+        default_outcome="needs_revision",
+    )
+    @listen(or_("generate_content", "needs_revision"))
+    def review_content(self):
+        return "Rascunho do post do blog aqui..."
 
-@listen("needs_revision")
-def revise(self, result):
-    print(f"Revisando baseado em: {result.feedback}")
+    @listen("approved")
+    def publish(self, result):
+        print(f"Publicando! Usuário disse: {result.feedback}")
+
+    @listen("rejected")
+    def discard(self, result):
+        print(f"Descartando. Motivo: {result.feedback}")
 ```
 
+Quando o humano diz algo como "precisa de mais detalhes", o LLM mapeia para `"needs_revision"`, que dispara `review_content` novamente via `or_()` — criando um loop de revisão. O loop continua até que o outcome seja `"approved"` ou `"rejected"`.
+
 <Tip>
 O LLM usa saídas estruturadas (function calling) quando disponível para garantir que a resposta seja um dos seus outcomes especificados. Isso torna o roteamento confiável e previsível.
 </Tip>
 
+<Warning>
+Um método `@start()` só executa uma vez no início do flow. Se você precisa de um loop de revisão, separe o método start do método de revisão e use `@listen(or_("trigger", "revision_outcome"))` no método de revisão para habilitar o self-loop.
+</Warning>
+
 ## HumanFeedbackResult
 
 O dataclass `HumanFeedbackResult` contém todas as informações sobre uma interação de feedback humano:
@@ -191,116 +203,162 @@ Aqui está um exemplo completo implementando um fluxo de revisão e aprovação
 <CodeGroup>
 
 ```python Code
-from crewai.flow.flow import Flow, start, listen
+from crewai.flow.flow import Flow, start, listen, or_
 from crewai.flow.human_feedback import human_feedback, HumanFeedbackResult
 from pydantic import BaseModel
 
 
 class ContentState(BaseModel):
-    topic: str = ""
     draft: str = ""
-    final_content: str = ""
     revision_count: int = 0
+    status: str = "pending"
 
 
 class ContentApprovalFlow(Flow[ContentState]):
-    """Um flow que gera conteúdo e obtém aprovação humana."""
+    """Um flow que gera conteúdo e faz loop até o humano aprovar."""
 
     @start()
-    def get_topic(self):
-        self.state.topic = input("Sobre qual tópico devo escrever? ")
-        return self.state.topic
-
-    @listen(get_topic)
-    def generate_draft(self, topic):
-        # Em uso real, isso chamaria um LLM
-        self.state.draft = f"# {topic}\n\nEste é um rascunho sobre {topic}..."
+    def generate_draft(self):
+        self.state.draft = "# IA Segura\n\nEste é um rascunho sobre IA Segura..."
         return self.state.draft
 
-    @listen(generate_draft)
     @human_feedback(
-        message="Por favor, revise este rascunho. Responda 'approved', 'rejected', ou forneça feedback de revisão:",
+        message="Por favor, revise este rascunho. Aprove, rejeite ou descreva o que precisa mudar:",
         emit=["approved", "rejected", "needs_revision"],
         llm="gpt-4o-mini",
         default_outcome="needs_revision",
     )
-    def review_draft(self, draft):
-        return draft
+    @listen(or_("generate_draft", "needs_revision"))
+    def review_draft(self):
+        self.state.revision_count += 1
+        return f"{self.state.draft} (v{self.state.revision_count})"
 
     @listen("approved")
     def publish_content(self, result: HumanFeedbackResult):
-        self.state.final_content = result.output
-        print("\n✅ Conteúdo aprovado e publicado!")
-        print(f"Comentário do revisor: {result.feedback}")
+        self.state.status = "published"
+        print(f"Conteúdo aprovado e publicado! Revisor disse: {result.feedback}")
         return "published"
 
     @listen("rejected")
     def handle_rejection(self, result: HumanFeedbackResult):
-        print("\n❌ Conteúdo rejeitado")
-        print(f"Motivo: {result.feedback}")
+        self.state.status = "rejected"
+        print(f"Conteúdo rejeitado. Motivo: {result.feedback}")
         return "rejected"
 
-    @listen("needs_revision")
-    def revise_content(self, result: HumanFeedbackResult):
-        self.state.revision_count += 1
-        print(f"\n📝 Revisão #{self.state.revision_count} solicitada")
-        print(f"Feedback: {result.feedback}")
 
-        # Em um flow real, você pode voltar para generate_draft
-        # Para este exemplo, apenas reconhecemos
-        return "revision_requested"
-
-
-# Executar o flow
 flow = ContentApprovalFlow()
 result = flow.kickoff()
-print(f"\nFlow concluído. Revisões solicitadas: {flow.state.revision_count}")
+print(f"\nFlow finalizado. Status: {flow.state.status}, Revisões: {flow.state.revision_count}")
 ```
 
 ```text Output
-Sobre qual tópico devo escrever? Segurança em IA
+==================================================
+OUTPUT FOR REVIEW:
+==================================================
+# IA Segura
+
+Este é um rascunho sobre IA Segura... (v1)
+==================================================
+
+Por favor, revise este rascunho. Aprove, rejeite ou descreva o que precisa mudar:
+(Press Enter to skip, or type your feedback)
+
+Your feedback: Preciso de mais detalhes sobre segurança em IA.
 
 ==================================================
 OUTPUT FOR REVIEW:
 ==================================================
-# Segurança em IA
+# IA Segura
 
-Este é um rascunho sobre Segurança em IA...
+Este é um rascunho sobre IA Segura... (v2)
 ==================================================
 
-Por favor, revise este rascunho. Responda 'approved', 'rejected', ou forneça feedback de revisão:
+Por favor, revise este rascunho. Aprove, rejeite ou descreva o que precisa mudar:
 (Press Enter to skip, or type your feedback)
 
 Your feedback: Parece bom, aprovado!
 
-✅ Conteúdo aprovado e publicado!
-Comentário do revisor: Parece bom, aprovado!
+Conteúdo aprovado e publicado! Revisor disse: Parece bom, aprovado!
 
-Flow concluído. Revisões solicitadas: 0
+Flow finalizado. Status: published, Revisões: 2
 ```
 
 </CodeGroup>
 
 ## Combinando com Outros Decoradores
 
-O decorador `@human_feedback` funciona com outros decoradores de flow. Coloque-o como o decorador mais interno (mais próximo da função):
+O decorador `@human_feedback` funciona com `@start()`, `@listen()` e `or_()`. Ambas as ordens de decoradores funcionam — o framework propaga atributos em ambas as direções — mas os padrões recomendados são:
 
 ```python Code
-# Correto: @human_feedback é o mais interno (mais próximo da função)
+# Revisão única no início do flow (sem self-loop)
 @start()
-@human_feedback(message="Revise isto:")
+@human_feedback(message="Revise isto:", emit=["approved", "rejected"], llm="gpt-4o-mini")
 def my_start_method(self):
     return "content"
 
+# Revisão linear em um listener (sem self-loop)
 @listen(other_method)
-@human_feedback(message="Revise isto também:")
+@human_feedback(message="Revise isto também:", emit=["good", "bad"], llm="gpt-4o-mini")
 def my_listener(self, data):
     return f"processed: {data}"
+
+# Self-loop: revisão que pode voltar para revisões
+@human_feedback(message="Aprovar ou revisar?", emit=["approved", "revise"], llm="gpt-4o-mini")
+@listen(or_("upstream_method", "revise"))
+def review_with_loop(self):
+    return "content for review"
 ```
 
-<Tip>
-Coloque `@human_feedback` como o decorador mais interno (último/mais próximo da função) para que ele envolva o método diretamente e possa capturar o valor de retorno antes de passar para o sistema de flow.
-</Tip>
+### Padrão de self-loop
+
+Para criar um loop de revisão, o método de revisão deve escutar **ambos** um gatilho upstream e seu próprio outcome de revisão usando `or_()`:
+
+```python Code
+@start()
+def generate(self):
+    return "initial draft"
+
+@human_feedback(
+    message="Aprovar ou solicitar alterações?",
+    emit=["revise", "approved"],
+    llm="gpt-4o-mini",
+    default_outcome="approved",
+)
+@listen(or_("generate", "revise"))
+def review(self):
+    return "content"
+
+@listen("approved")
+def publish(self):
+    return "published"
+```
+
+Quando o outcome é `"revise"`, o flow roteia de volta para `review` (porque ele escuta `"revise"` via `or_()`). Quando o outcome é `"approved"`, o flow continua para `publish`. Isso funciona porque o engine de flow isenta roteadores da regra "fire once", permitindo que eles re-executem em cada iteração do loop.
+
+### Roteadores encadeados
+
+Um listener disparado pelo outcome de um roteador pode ser ele mesmo um roteador:
+
+```python Code
+@start()
+@human_feedback(message="Primeira revisão:", emit=["approved", "rejected"], llm="gpt-4o-mini")
+def draft(self):
+    return "draft content"
+
+@listen("approved")
+@human_feedback(message="Revisão final:", emit=["publish", "revise"], llm="gpt-4o-mini")
+def final_review(self, prev):
+    return "final content"
+
+@listen("publish")
+def on_publish(self, prev):
+    return "published"
+```
+
+### Limitações
+
+- **Métodos `@start()` executam uma vez**: Um método `@start()` não pode fazer self-loop. Se você precisa de um ciclo de revisão, use um método `@start()` separado como ponto de entrada e coloque o `@human_feedback` em um método `@listen()`.
+- **Sem `@start()` + `@listen()` no mesmo método**: Esta é uma restrição do framework de Flow. Um método é ou um ponto de início ou um listener, não ambos.
 
 ## Melhores Práticas
 
@@ -514,9 +572,9 @@ class ContentPipeline(Flow):
     @start()
     @human_feedback(
         message="Aprova este conteúdo para publicação?",
-        emit=["approved", "rejected", "needs_revision"],
+        emit=["approved", "rejected"],
         llm="gpt-4o-mini",
-        default_outcome="needs_revision",
+        default_outcome="rejected",
         provider=SlackNotificationProvider("#content-reviews"),
     )
     def generate_content(self):
@@ -532,11 +590,6 @@ class ContentPipeline(Flow):
         print(f"Arquivado. Motivo: {result.feedback}")
         return {"status": "archived"}
 
-    @listen("needs_revision")
-    def queue_revision(self, result):
-        print(f"Na fila para revisão: {result.feedback}")
-        return {"status": "revision_needed"}
-
 
 # Iniciando o flow (vai pausar e aguardar resposta do Slack)
 def start_content_pipeline():
@@ -576,6 +629,64 @@ Se você está usando um framework web assíncrono (FastAPI, aiohttp, Slack Bolt
 5. **Persistência automática**: O estado é automaticamente salvo quando `HumanFeedbackPending` é lançado e usa `SQLiteFlowPersistence` por padrão
 6. **Persistência customizada**: Passe uma instância de persistência customizada para `from_pending()` se necessário
 
+## Aprendendo com Feedback
+
+O parâmetro `learn=True` habilita um ciclo de feedback entre revisores humanos e o sistema de memória. Quando habilitado, o sistema melhora progressivamente suas saídas aprendendo com correções humanas anteriores.
+
+### Como Funciona
+
+1. **Após o feedback**: O LLM extrai lições generalizáveis da saída + feedback e as armazena na memória com `source="hitl"`. Se o feedback for apenas aprovação (ex: "parece bom"), nada é armazenado.
+2. **Antes da próxima revisão**: Lições HITL passadas são recuperadas da memória e aplicadas pelo LLM para melhorar a saída antes que o humano a veja.
+
+Com o tempo, o humano vê saídas pré-revisadas progressivamente melhores porque cada correção informa revisões futuras.
+
+### Exemplo
+
+```python Code
+class ArticleReviewFlow(Flow):
+    @start()
+    def generate_article(self):
+        return self.crew.kickoff(inputs={"topic": "AI Safety"}).raw
+
+    @human_feedback(
+        message="Revise este rascunho do artigo:",
+        emit=["approved", "needs_revision"],
+        llm="gpt-4o-mini",
+        learn=True,  # enable HITL learning
+    )
+    @listen(or_("generate_article", "needs_revision"))
+    def review_article(self):
+        return self.last_human_feedback.output if self.last_human_feedback else "article draft"
+
+    @listen("approved")
+    def publish(self):
+        print(f"Publishing: {self.last_human_feedback.output}")
+```
+
+**Primeira execução**: O humano vê a saída bruta e diz "Sempre inclua citações para afirmações factuais." A lição é destilada e armazenada na memória.
+
+**Segunda execução**: O sistema recupera a lição sobre citações, pré-revisa a saída para adicionar citações e então mostra a versão melhorada. O trabalho do humano muda de "corrigir tudo" para "identificar o que o sistema deixou passar."
+
+### Configuração
+
+| Parâmetro | Padrão | Descrição |
+|-----------|--------|-----------|
+| `learn` | `False` | Habilitar aprendizado HITL |
+| `learn_limit` | `5` | Máximo de lições passadas para recuperar na pré-revisão |
+
+### Decisões de Design Principais
+
+- **Mesmo LLM para tudo**: O parâmetro `llm` no decorador é compartilhado pelo mapeamento de outcome, destilação de lições e pré-revisão. Não é necessário configurar múltiplos modelos.
+- **Saída estruturada**: Tanto a destilação quanto a pré-revisão usam function calling com modelos Pydantic quando o LLM suporta, com fallback para parsing de texto caso contrário.
+- **Armazenamento não-bloqueante**: Lições são armazenadas via `remember_many()` que executa em uma thread em segundo plano -- o flow continua imediatamente.
+- **Degradação graciosa**: Se o LLM falhar durante a destilação, nada é armazenado. Se falhar durante a pré-revisão, a saída bruta é mostrada. Nenhuma falha bloqueia o flow.
+- **Sem escopo/categorias necessários**: Ao armazenar lições, apenas `source` é passado. O pipeline de codificação infere escopo, categorias e importância automaticamente.
+
+<Note>
+`learn=True` requer que o Flow tenha memória disponível. Flows obtêm memória automaticamente por padrão, mas se você a desabilitou com `_skip_auto_memory`, o aprendizado HITL será silenciosamente ignorado.
+</Note>
+
+
 ## Documentação Relacionada
 
 - [Visão Geral de Flows](/pt-BR/concepts/flows) - Aprenda sobre CrewAI Flows
@@ -583,3 +694,4 @@ Se você está usando um framework web assíncrono (FastAPI, aiohttp, Slack Bolt
 - [Persistência de Flows](/pt-BR/concepts/flows#persistence) - Persistindo estado de flows
 - [Roteamento com @router](/pt-BR/concepts/flows#router) - Mais sobre roteamento condicional
 - [Input Humano na Execução](/pt-BR/learn/human-input-on-execution) - Input humano no nível de task
+- [Memória](/pt-BR/concepts/memory) - O sistema unificado de memória usado pelo aprendizado HITL

lib/crewai-tools/src/crewai_tools/tools/nl2sql/README.md

@@ -8,6 +8,29 @@ This enables multiple workflows like having an Agent to access the database fetc
 
 **Attention**: Make sure that the Agent has access to a Read-Replica or that is okay for the Agent to run insert/update queries on the database.
 
+## Security Model
+
+`NL2SQLTool` is an execution-capable tool. It runs model-generated SQL directly against the configured database connection.
+
+Risk depends on deployment choices:
+
+- Which credentials are used in `db_uri`
+- Whether untrusted input can influence prompts
+- Whether tool-call guardrails are enforced before execution
+
+If untrusted input can reach this tool, treat the integration as high risk.
+
+## Hardening Recommendations
+
+Use all of the following in production:
+
+- Use a read-only database user whenever possible
+- Prefer a read replica for analytics/retrieval workloads
+- Grant least privilege (no superuser/admin roles, no file/system-level capabilities)
+- Apply database-side resource limits (statement timeout, lock timeout, cost/row limits)
+- Add `before_tool_call` hooks to enforce allowed query patterns
+- Enable query logging and alerting for destructive statements
+
 ## Requirements
 
 - SqlAlchemy

lib/crewai-tools/tests/tools/brave_search_tool_test.py

@@ -33,8 +33,11 @@ def test_brave_tool_search(mock_get, brave_tool):
     mock_get.return_value.json.return_value = mock_response
 
     result = brave_tool.run(query="test")
-    assert "Test Title" in result
-    assert "http://test.com" in result
+    data = json.loads(result)
+    assert isinstance(data, list)
+    assert len(data) >= 1
+    assert data[0]["title"] == "Test Title"
+    assert data[0]["url"] == "http://test.com"
 
 
 @patch("requests.get")

lib/crewai/pyproject.toml

@@ -26,6 +26,8 @@ dependencies = [
     # Authentication and Security
     "python-dotenv~=1.1.1",
     "pyjwt>=2.9.0,<3",
+    # TUI
+    "textual>=7.5.0",
     # Configuration and Utils
     "click~=8.1.7",
     "appdirs~=1.4.4",
@@ -39,6 +41,7 @@ dependencies = [
     "mcp~=1.26.0",
     "uv~=0.9.13",
     "aiosqlite~=0.21.0",
+    "lancedb>=0.4.0",
 ]
 
 [project.urls]

lib/crewai/src/crewai/__init__.py

@@ -10,6 +10,7 @@ from crewai.flow.flow import Flow
 from crewai.knowledge.knowledge import Knowledge
 from crewai.llm import LLM
 from crewai.llms.base_llm import BaseLLM
+from crewai.memory.unified_memory import Memory
 from crewai.process import Process
 from crewai.task import Task
 from crewai.tasks.llm_guardrail import LLMGuardrail
@@ -80,6 +81,7 @@ __all__ = [
     "Flow",
     "Knowledge",
     "LLMGuardrail",
+    "Memory",
     "Process",
     "Task",
     "TaskOutput",

lib/crewai/src/crewai/agent/core.py

@@ -71,7 +71,6 @@ from crewai.mcp import (
 from crewai.mcp.transports.http import HTTPTransport
 from crewai.mcp.transports.sse import SSETransport
 from crewai.mcp.transports.stdio import StdioTransport
-from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.rag.embeddings.types import EmbedderConfig
 from crewai.security.fingerprint import Fingerprint
 from crewai.tools.agent_tools.agent_tools import AgentTools
@@ -311,19 +310,12 @@ class Agent(BaseAgent):
             raise ValueError(f"Invalid Knowledge Configuration: {e!s}") from e
 
     def _is_any_available_memory(self) -> bool:
-        """Check if any memory is available."""
-        if not self.crew:
-            return False
-
-        memory_attributes = [
-            "memory",
-            "_short_term_memory",
-            "_long_term_memory",
-            "_entity_memory",
-            "_external_memory",
-        ]
-
-        return any(getattr(self.crew, attr) for attr in memory_attributes)
+        """Check if unified memory is available (agent or crew)."""
+        if getattr(self, "memory", None):
+            return True
+        if self.crew and getattr(self.crew, "_memory", None):
+            return True
+        return False
 
     def _supports_native_tool_calling(self, tools: list[BaseTool]) -> bool:
         """Check if the LLM supports native function calling with the given tools.
@@ -387,15 +379,16 @@ class Agent(BaseAgent):
             memory = ""
 
             try:
-                contextual_memory = ContextualMemory(
-                    self.crew._short_term_memory,
-                    self.crew._long_term_memory,
-                    self.crew._entity_memory,
-                    self.crew._external_memory,
-                    agent=self,
-                    task=task,
+                unified_memory = getattr(self, "memory", None) or (
+                    getattr(self.crew, "_memory", None) if self.crew else None
                 )
-                memory = contextual_memory.build_context_for_task(task, context or "")
+                if unified_memory is not None:
+                    query = task.description
+                    matches = unified_memory.recall(query, limit=10)
+                    if matches:
+                        memory = "Relevant memories:\n" + "\n".join(
+                            f"- {m.record.content}" for m in matches
+                        )
                 if memory.strip() != "":
                     task_prompt += self.i18n.slice("memory").format(memory=memory)
 
@@ -624,17 +617,16 @@ class Agent(BaseAgent):
             memory = ""
 
             try:
-                contextual_memory = ContextualMemory(
-                    self.crew._short_term_memory,
-                    self.crew._long_term_memory,
-                    self.crew._entity_memory,
-                    self.crew._external_memory,
-                    agent=self,
-                    task=task,
-                )
-                memory = await contextual_memory.abuild_context_for_task(
-                    task, context or ""
+                unified_memory = getattr(self, "memory", None) or (
+                    getattr(self.crew, "_memory", None) if self.crew else None
                 )
+                if unified_memory is not None:
+                    query = task.description
+                    matches = unified_memory.recall(query, limit=10)
+                    if matches:
+                        memory = "Relevant memories:\n" + "\n".join(
+                            f"- {m.record.content}" for m in matches
+                        )
                 if memory.strip() != "":
                     task_prompt += self.i18n.slice("memory").format(memory=memory)
 
@@ -1712,6 +1704,18 @@ class Agent(BaseAgent):
 
         # Prepare tools
         raw_tools: list[BaseTool] = self.tools or []
+
+        # Inject memory tools for standalone kickoff (crew path handles its own)
+        agent_memory = getattr(self, "memory", None)
+        if agent_memory is not None:
+            from crewai.tools.memory_tools import create_memory_tools
+
+            existing_names = {sanitize_tool_name(t.name) for t in raw_tools}
+            raw_tools.extend(
+                mt for mt in create_memory_tools(agent_memory)
+                if sanitize_tool_name(mt.name) not in existing_names
+            )
+
         parsed_tools = parse_tools(raw_tools)
 
         # Build agent_info for backward-compatible event emission
@@ -1786,6 +1790,49 @@ class Agent(BaseAgent):
         if input_files:
             all_files.update(input_files)
 
+        # Inject memory context for standalone kickoff (recall before execution)
+        if agent_memory is not None:
+            try:
+                crewai_event_bus.emit(
+                    self,
+                    event=MemoryRetrievalStartedEvent(
+                        task_id=None,
+                        source_type="agent_kickoff",
+                        from_agent=self,
+                    ),
+                )
+                start_time = time.time()
+                matches = agent_memory.recall(formatted_messages, limit=10)
+                memory_block = ""
+                if matches:
+                    memory_block = "Relevant memories:\n" + "\n".join(
+                        f"- {m.record.content}" for m in matches
+                    )
+                if memory_block:
+                    formatted_messages += "\n\n" + self.i18n.slice("memory").format(
+                        memory=memory_block
+                    )
+                crewai_event_bus.emit(
+                    self,
+                    event=MemoryRetrievalCompletedEvent(
+                        task_id=None,
+                        memory_content=memory_block,
+                        retrieval_time_ms=(time.time() - start_time) * 1000,
+                        source_type="agent_kickoff",
+                        from_agent=self,
+                    ),
+                )
+            except Exception as e:
+                crewai_event_bus.emit(
+                    self,
+                    event=MemoryRetrievalFailedEvent(
+                        task_id=None,
+                        source_type="agent_kickoff",
+                        from_agent=self,
+                        error=str(e),
+                    ),
+                )
+
         # Build the input dict for the executor
         inputs: dict[str, Any] = {
             "input": formatted_messages,
@@ -1856,6 +1903,9 @@ class Agent(BaseAgent):
                     response_format=response_format,
                 )
 
+            # Save to memory after execution (passive save)
+            self._save_kickoff_to_memory(messages, output.raw)
+
             crewai_event_bus.emit(
                 self,
                 event=LiteAgentExecutionCompletedEvent(
@@ -1876,6 +1926,31 @@ class Agent(BaseAgent):
             )
             raise
 
+    def _save_kickoff_to_memory(
+        self, messages: str | list[LLMMessage], output_text: str
+    ) -> None:
+        """Save kickoff result to memory. No-op if agent has no memory."""
+        agent_memory = getattr(self, "memory", None)
+        if agent_memory is None:
+            return
+        try:
+            if isinstance(messages, str):
+                input_str = messages
+            else:
+                input_str = "\n".join(
+                    str(msg.get("content", "")) for msg in messages if msg.get("content")
+                ) or "User request"
+            raw = (
+                f"Input: {input_str}\n"
+                f"Agent: {self.role}\n"
+                f"Result: {output_text}"
+            )
+            extracted = agent_memory.extract_memories(raw)
+            if extracted:
+                agent_memory.remember_many(extracted)
+        except Exception as e:
+            self._logger.log("error", f"Failed to save kickoff result to memory: {e}")
+
     def _execute_and_build_output(
         self,
         executor: AgentExecutor,
@@ -2158,6 +2233,9 @@ class Agent(BaseAgent):
                     response_format=response_format,
                 )
 
+            # Save to memory after async execution (passive save)
+            self._save_kickoff_to_memory(messages, output.raw)
+
             crewai_event_bus.emit(
                 self,
                 event=LiteAgentExecutionCompletedEvent(

lib/crewai/src/crewai/agents/agent_builder/base_agent.py

@@ -199,6 +199,14 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         default=None,
         description="List of MCP server references. Supports 'https://server.com/path' for external servers and 'crewai-amp:mcp-name' for AMP marketplace. Use '#tool_name' suffix for specific tools.",
     )
+    memory: Any = Field(
+        default=None,
+        description=(
+            "Enable agent memory. Pass True for default Memory(), "
+            "or a Memory/MemoryScope/MemorySlice instance for custom configuration. "
+            "If not set, falls back to crew memory."
+        ),
+    )
 
     @model_validator(mode="before")
     @classmethod
@@ -329,6 +337,17 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
             self._token_process = TokenProcess()
         return self
 
+    @model_validator(mode="after")
+    def resolve_memory(self) -> Self:
+        """Resolve memory field: True creates a default Memory(), instance is used as-is."""
+        if self.memory is True:
+            from crewai.memory.unified_memory import Memory
+
+            self.memory = Memory()
+        elif self.memory is False:
+            self.memory = None
+        return self
+
     @property
     def key(self) -> str:
         source = [

lib/crewai/src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -1,13 +1,8 @@
 from __future__ import annotations
 
-import time
 from typing import TYPE_CHECKING
 
 from crewai.agents.parser import AgentFinish
-from crewai.memory.entity.entity_memory_item import EntityMemoryItem
-from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
-from crewai.utilities.converter import ConverterError
-from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.printer import Printer
 from crewai.utilities.string_utils import sanitize_tool_name
 
@@ -30,110 +25,29 @@ class CrewAgentExecutorMixin:
     _i18n: I18N
     _printer: Printer = Printer()
 
-    def _create_short_term_memory(self, output: AgentFinish) -> None:
-        """Create and save a short-term memory item if conditions are met."""
+    def _save_to_memory(self, output: AgentFinish) -> None:
+        """Save task result to unified memory (memory or crew._memory)."""
+        memory = getattr(self.agent, "memory", None) or (
+            getattr(self.crew, "_memory", None) if self.crew else None
+        )
+        if memory is None or not self.task:
+            return
         if (
-            self.crew
-            and self.agent
-            and self.task
-            and f"Action: {sanitize_tool_name('Delegate work to coworker')}"
-            not in output.text
+            f"Action: {sanitize_tool_name('Delegate work to coworker')}"
+            in output.text
         ):
-            try:
-                if (
-                    hasattr(self.crew, "_short_term_memory")
-                    and self.crew._short_term_memory
-                ):
-                    self.crew._short_term_memory.save(
-                        value=output.text,
-                        metadata={
-                            "observation": self.task.description,
-                        },
-                    )
-            except Exception as e:
-                self.agent._logger.log(
-                    "error", f"Failed to add to short term memory: {e}"
-                )
-
-    def _create_external_memory(self, output: AgentFinish) -> None:
-        """Create and save a external-term memory item if conditions are met."""
-        if (
-            self.crew
-            and self.agent
-            and self.task
-            and hasattr(self.crew, "_external_memory")
-            and self.crew._external_memory
-        ):
-            try:
-                self.crew._external_memory.save(
-                    value=output.text,
-                    metadata={
-                        "description": self.task.description,
-                        "messages": self.messages,
-                    },
-                )
-            except Exception as e:
-                self.agent._logger.log(
-                    "error", f"Failed to add to external memory: {e}"
-                )
-
-    def _create_long_term_memory(self, output: AgentFinish) -> None:
-        """Create and save long-term and entity memory items based on evaluation."""
-        if (
-            self.crew
-            and self.crew._long_term_memory
-            and self.crew._entity_memory
-            and self.task
-            and self.agent
-        ):
-            try:
-                ltm_agent = TaskEvaluator(self.agent)
-                evaluation = ltm_agent.evaluate(self.task, output.text)
-
-                if isinstance(evaluation, ConverterError):
-                    return
-
-                long_term_memory = LongTermMemoryItem(
-                    task=self.task.description,
-                    agent=self.agent.role,
-                    quality=evaluation.quality,
-                    datetime=str(time.time()),
-                    expected_output=self.task.expected_output,
-                    metadata={
-                        "suggestions": evaluation.suggestions,
-                        "quality": evaluation.quality,
-                    },
-                )
-                self.crew._long_term_memory.save(long_term_memory)
-
-                entity_memories = [
-                    EntityMemoryItem(
-                        name=entity.name,
-                        type=entity.type,
-                        description=entity.description,
-                        relationships="\n".join(
-                            [f"- {r}" for r in entity.relationships]
-                        ),
-                    )
-                    for entity in evaluation.entities
-                ]
-                if entity_memories:
-                    self.crew._entity_memory.save(entity_memories)
-            except AttributeError as e:
-                self.agent._logger.log(
-                    "error", f"Missing attributes for long term memory: {e}"
-                )
-            except Exception as e:
-                self.agent._logger.log(
-                    "error", f"Failed to add to long term memory: {e}"
-                )
-        elif (
-            self.crew
-            and self.crew._long_term_memory
-            and self.crew._entity_memory is None
-        ):
-            if self.agent and self.agent.verbose:
-                self._printer.print(
-                    content="Long term memory is enabled, but entity memory is not enabled. Please configure entity memory or set memory=True to automatically enable it.",
-                    color="bold_yellow",
-                )
+            return
+        try:
+            raw = (
+                f"Task: {self.task.description}\n"
+                f"Agent: {self.agent.role}\n"
+                f"Expected result: {self.task.expected_output}\n"
+                f"Result: {output.text}"
+            )
+            extracted = memory.extract_memories(raw)
+            if extracted:
+                memory.remember_many(extracted, agent_role=self.agent.role)
+        except Exception as e:
+            self.agent._logger.log(
+                "error", f"Failed to save to memory: {e}"
+            )

lib/crewai/src/crewai/agents/crew_agent_executor.py

@@ -234,9 +234,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         if self.ask_for_human_input:
             formatted_answer = self._handle_human_feedback(formatted_answer)
 
-        self._create_short_term_memory(formatted_answer)
-        self._create_long_term_memory(formatted_answer)
-        self._create_external_memory(formatted_answer)
+        self._save_to_memory(formatted_answer)
         return {"output": formatted_answer.output}
 
     def _inject_multimodal_files(self, inputs: dict[str, Any] | None = None) -> None:
@@ -1011,9 +1009,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         if self.ask_for_human_input:
             formatted_answer = await self._ahandle_human_feedback(formatted_answer)
 
-        self._create_short_term_memory(formatted_answer)
-        self._create_long_term_memory(formatted_answer)
-        self._create_external_memory(formatted_answer)
+        self._save_to_memory(formatted_answer)
         return {"output": formatted_answer.output}
 
     async def _ainvoke_loop(self) -> AgentFinish:

lib/crewai/src/crewai/cli/cli.py

@@ -1,6 +1,7 @@
 from importlib.metadata import version as get_version
 import os
 import subprocess
+from typing import Any
 
 import click
 
@@ -179,9 +180,19 @@ def log_tasks_outputs() -> None:
 
 
 @crewai.command()
-@click.option("-l", "--long", is_flag=True, help="Reset LONG TERM memory")
-@click.option("-s", "--short", is_flag=True, help="Reset SHORT TERM memory")
-@click.option("-e", "--entities", is_flag=True, help="Reset ENTITIES memory")
+@click.option("-m", "--memory", is_flag=True, help="Reset MEMORY")
+@click.option(
+    "-l", "--long", is_flag=True, hidden=True,
+    help="[Deprecated: use --memory] Reset memory",
+)
+@click.option(
+    "-s", "--short", is_flag=True, hidden=True,
+    help="[Deprecated: use --memory] Reset memory",
+)
+@click.option(
+    "-e", "--entities", is_flag=True, hidden=True,
+    help="[Deprecated: use --memory] Reset memory",
+)
 @click.option("-kn", "--knowledge", is_flag=True, help="Reset KNOWLEDGE storage")
 @click.option(
     "-akn", "--agent-knowledge", is_flag=True, help="Reset AGENT KNOWLEDGE storage"
@@ -191,6 +202,7 @@ def log_tasks_outputs() -> None:
 )
 @click.option("-a", "--all", is_flag=True, help="Reset ALL memories")
 def reset_memories(
+    memory: bool,
     long: bool,
     short: bool,
     entities: bool,
@@ -200,13 +212,22 @@ def reset_memories(
     all: bool,
 ) -> None:
     """
-    Reset the crew memories (long, short, entity, latest_crew_kickoff_ouputs, knowledge, agent_knowledge). This will delete all the data saved.
+    Reset the crew memories (memory, knowledge, agent_knowledge, kickoff_outputs). This will delete all the data saved.
     """
     try:
+        # Treat legacy flags as --memory with a deprecation warning
+        if long or short or entities:
+            legacy_used = [
+                f for f, v in [("--long", long), ("--short", short), ("--entities", entities)] if v
+            ]
+            click.echo(
+                f"Warning: {', '.join(legacy_used)} {'is' if len(legacy_used) == 1 else 'are'} "
+                "deprecated. Use --memory (-m) instead. All memory is now unified."
+            )
+            memory = True
+
         memory_types = [
-            long,
-            short,
-            entities,
+            memory,
             knowledge,
             agent_knowledge,
             kickoff_outputs,
@@ -218,12 +239,73 @@ def reset_memories(
             )
             return
         reset_memories_command(
-            long, short, entities, knowledge, agent_knowledge, kickoff_outputs, all
+            memory, knowledge, agent_knowledge, kickoff_outputs, all
         )
     except Exception as e:
         click.echo(f"An error occurred while resetting memories: {e}", err=True)
 
 
+@crewai.command()
+@click.option(
+    "--storage-path",
+    type=str,
+    default=None,
+    help="Path to LanceDB memory directory. If omitted, uses ./.crewai/memory.",
+)
+@click.option(
+    "--embedder-provider",
+    type=str,
+    default=None,
+    help="Embedder provider for recall queries (e.g. openai, google-vertex, cohere, ollama).",
+)
+@click.option(
+    "--embedder-model",
+    type=str,
+    default=None,
+    help="Embedder model name (e.g. text-embedding-3-small, gemini-embedding-001).",
+)
+@click.option(
+    "--embedder-config",
+    type=str,
+    default=None,
+    help='Full embedder config as JSON (e.g. \'{"provider": "cohere", "config": {"model_name": "embed-v4.0"}}\').',
+)
+def memory(
+    storage_path: str | None,
+    embedder_provider: str | None,
+    embedder_model: str | None,
+    embedder_config: str | None,
+) -> None:
+    """Open the Memory TUI to browse scopes and recall memories."""
+    try:
+        from crewai.cli.memory_tui import MemoryTUI
+    except ImportError as exc:
+        click.echo(
+            "Textual is required for the memory TUI but could not be imported. "
+            "Try reinstalling crewai or: pip install textual"
+        )
+        raise SystemExit(1) from exc
+
+    # Build embedder spec from CLI flags.
+    embedder_spec: dict[str, Any] | None = None
+    if embedder_config:
+        import json as _json
+
+        try:
+            embedder_spec = _json.loads(embedder_config)
+        except _json.JSONDecodeError as exc:
+            click.echo(f"Invalid --embedder-config JSON: {exc}")
+            raise SystemExit(1) from exc
+    elif embedder_provider:
+        cfg: dict[str, str] = {}
+        if embedder_model:
+            cfg["model_name"] = embedder_model
+        embedder_spec = {"provider": embedder_provider, "config": cfg}
+
+    app = MemoryTUI(storage_path=storage_path, embedder_config=embedder_spec)
+    app.run()
+
+
 @crewai.command()
 @click.option(
     "-n",