diff --git a/src/crewai/crew.py b/src/crewai/crew.py
index 5e08f59b8..5a1fc87fe 100644
--- a/src/crewai/crew.py
+++ b/src/crewai/crew.py
@@ -6,15 +6,15 @@ from typing import Any, Dict, List, Optional, Tuple, Union
 
 from langchain_core.callbacks import BaseCallbackHandler
 from pydantic import (
-  UUID4,
-  BaseModel,
-  ConfigDict,
-  Field,
-  InstanceOf,
-  Json,
-  PrivateAttr,
-  field_validator,
-  model_validator,
+    UUID4,
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    Json,
+    PrivateAttr,
+    field_validator,
+    model_validator,
 )
 from pydantic_core import PydanticCustomError
 
@@ -656,5 +656,27 @@ class Crew(BaseModel):
             )
         self._telemetry.end_crew(self, final_string_output)
 
+    def calculate_usage_metrics(self) -> Dict[str, int]:
+        """Calculates and returns the usage metrics."""
+        total_usage_metrics = {
+            "total_tokens": 0,
+            "prompt_tokens": 0,
+            "completion_tokens": 0,
+            "successful_requests": 0,
+        }
+
+        for agent in self.agents:
+            if hasattr(agent, "_token_process"):
+                token_sum = agent._token_process.get_summary()
+                for key in total_usage_metrics:
+                    total_usage_metrics[key] += token_sum.get(key, 0)
+
+        if self.manager_agent and hasattr(self.manager_agent, "_token_process"):
+            token_sum = self.manager_agent._token_process.get_summary()
+            for key in total_usage_metrics:
+                total_usage_metrics[key] += token_sum.get(key, 0)
+
+        return total_usage_metrics
+
     def __repr__(self):
         return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"
diff --git a/src/crewai/crews/crew_output.py b/src/crewai/crews/crew_output.py
index 99a8e37bc..018fc76ff 100644
--- a/src/crewai/crews/crew_output.py
+++ b/src/crewai/crews/crew_output.py
@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Union
+from typing import Any, Dict, List
 
 from pydantic import BaseModel, Field
 
@@ -18,7 +18,7 @@ class CrewOutput(BaseModel):
     # TODO: Ask @joao what is the desired behavior here
     def result(
         self,
-    ) -> List[str | BaseModel | Dict[str, Any]]]:
+    ) -> List[str | BaseModel | Dict[str, Any]]:
         """Return the result of the task based on the available output."""
         results = [output.result() for output in self.output]
         return results
diff --git a/src/crewai/task.py b/src/crewai/task.py
index 5ac6fad63..06d2808df 100644
--- a/src/crewai/task.py
+++ b/src/crewai/task.py
@@ -217,7 +217,7 @@ class Task(BaseModel):
                 f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
             )
 
-        self._execution_span = self._telemetry.task_started(self)
+        self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
 
         if self.context:
             task_outputs: List[TaskOutput] = []
diff --git a/tests/agent_test.py b/tests/agent_test.py
index 7c0f3c242..cb4a63bc9 100644
--- a/tests/agent_test.py
+++ b/tests/agent_test.py
@@ -4,10 +4,6 @@ from unittest import mock
 from unittest.mock import patch
 
 import pytest
-from langchain.tools import tool
-from langchain_core.exceptions import OutputParserException
-from langchain_openai import ChatOpenAI
-
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.executor import CrewAgentExecutor
@@ -15,6 +11,9 @@ from crewai.agents.parser import CrewAgentParser
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.utilities import RPMController
+from langchain.tools import tool
+from langchain_core.exceptions import OutputParserException
+from langchain_openai import ChatOpenAI
 
 
 def test_agent_creation():
@@ -631,8 +630,8 @@ def test_agent_use_specific_tasks_output_as_context(capsys):
 
     crew = Crew(agents=[agent1, agent2], tasks=tasks)
     result = crew.kickoff()
-    assert "bye" not in result.lower()
-    assert "hi" in result.lower() or "hello" in result.lower()
+    assert "bye" not in result.raw_output().lower()
+    assert "hi" in result.raw_output().lower() or "hello" in result.raw_output().lower()
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -750,7 +749,8 @@ def test_tool_result_as_answer_is_the_final_answer_for_the_agent():
     crew = Crew(agents=[agent1], tasks=tasks)
 
     result = crew.kickoff()
-    assert result == "Howdy!"
+    print("RESULT: ", result.raw_output())
+    assert result.raw_output() == "Howdy!"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])