Skip to main content

​
Installation

pip install pandaprobe[crewai]

​
Setup

from pandaprobe.integrations.crewai import CrewAIAdapter

adapter = CrewAIAdapter(
    session_id="conversation-123",
    user_id="user-abc",
    tags=["production"],
)
adapter.instrument()

​
Usage

from crewai import Agent, Task, Crew

researcher = Agent(
    role="Research Analyst",
    goal="Find the latest AI trends",
    backstory="You are an expert AI researcher.",
)

task = Task(
    description="Research the latest developments in AI agents.",
    expected_output="A summary of key trends.",
    agent=researcher,
)

crew = Crew(agents=[researcher], tasks=[task])
result = crew.kickoff()

​
What gets traced

CrewAI ComponentSpan KindDescription
Crew.kickoff / kickoff_for_eachCHAINRoot trace boundary, crew configuration as system message
Agent.execute_taskAGENTAgent backstory as system message, prior agent context
LLM completion callsLLMToken delta tracking (per-call usage), reasoning extraction
execute_tool_and_check_finalityTOOLTool name from AgentAction, input/output

​
Multi-agent support

In multi-agent crews, PandaProbe tracks context propagation between agents. Each agent’s output is made available as context for subsequent agents, and this is reflected in the trace hierarchy.

​
Token usage

CrewAI token usage is computed using delta tracking: the adapter snapshots the agent’s cumulative _token_usage before and after each LLM call to determine per-call token counts.
CrewAI FieldPandaProbe Field
prompt_tokensprompt_tokens
completion_tokenscompletion_tokens
total_tokenstotal_tokens
cached_prompt_tokenscache_read_tokens
reasoning_tokensreasoning_tokens