---
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