Tracing in CrewAI

Tracing helps you understand what’s happening under the hood when an agent run is called. You get to understand the path, tools calls made, context used, latency taken when you run your agent using TrueFoundry’s tracing functionality.

TrueFoundry enhances CrewAI with powerful observability features, offering real-time monitoring of AI agent workflows, task execution, and LLM performance. By integrating with TrueFoundry's tracing, metrics collection, and error detection capabilities, you gain deep insights into how CrewAI agents interact, complete tasks, and optimize workflows. Additionally, TrueFoundry provides end-to-end traceability for AI-driven systems, making your CrewAI implementations more transparent, reliable, and scalable.

lnstall dependencies:

First, you need to install the following

pip install crewai==0.102.0 langchain-openai==0.2.14 traceloop-sdk==0.38.12

Setup environment variables:

Add the necessary environment variables to enable tracing

OPENAI_API_KEY=sk-proj-*
TRACELOOP_BASE_URL=<<control-plane-url>>/api/otel
TRACELOOP_HEADERS="Authorization=Bearer <<api-key>>

Generate API key from here

Demo CrewAI Agent

The following demo agent is a research agent which researches the latest trends to conduct detailed market research with keen attention to detail. For example, it can generate "A comprehensive report on AI and machine learning"

from crewai import Agent, Task, Crew
from langchain_openai import ChatOpenAI

#Import Traceloop
from traceloop.sdk import Traceloop 

#Initialize Traceloop SDK to log traces automatically
Traceloop.init(app_name="crewai")

llm = ChatOpenAI(model="gpt-4o-mini")

researcher = Agent(
    role='Research Analyst',
    goal='Conduct detailed market research',
    backstory='Expert in market analysis with keen attention to detail',
    llm=llm,
    verbose=True
)

research_task = Task(
    description='Research the latest trends in AI and machine learning',
    agent=researcher,
    expected_output='A comprehensive report on current AI and machine learning trends',
    expected_output_type=str
)

crew = Crew(
    agents=[researcher],
    tasks=[research_task],
    verbose=True
)

result = crew.kickoff()
print("Final Result:", result)

View Logged Trace on UI