> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Async Team Post-Hook Agent as Judge

> Automatic async evaluation of team outputs using post-hooks

This example demonstrates using Agent as Judge as an async post-hook on a Team to automatically evaluate team responses.

<Steps>
  <Step title="Add the following code to your Python file">
    ```python agent_as_judge_team_post_hook_async.py theme={null}
    import asyncio

    from agno.agent import Agent
    from agno.db.sqlite import AsyncSqliteDb
    from agno.eval.agent_as_judge import AgentAsJudgeEval
    from agno.models.openai import OpenAIResponses
    from agno.team.team import Team


    async def main():
        # Setup database to persist eval results
        db = AsyncSqliteDb(db_file="tmp/agent_as_judge_team_post_hook_async.db")

        # Eval runs as post-hook, results saved to database
        agent_as_judge_eval = AgentAsJudgeEval(
            name="Team Response Quality",
            model=OpenAIResponses(id="gpt-5.2"),
            criteria="Response should be well-researched, clear, comprehensive, and show good collaboration between team members",
            scoring_strategy="numeric",
            threshold=7,
            db=db,
        )

        # Setup a team with researcher and writer
        researcher = Agent(
            name="Researcher",
            role="Research and gather information",
            model=OpenAIResponses(id="gpt-5.2"),
        )

        writer = Agent(
            name="Writer",
            role="Write clear and concise summaries",
            model=OpenAIResponses(id="gpt-5.2"),
        )

        research_team = Team(
            name="Research Team",
            model=OpenAIResponses(id="gpt-5.2"),
            members=[researcher, writer],
            instructions=["First research the topic thoroughly, then write a clear summary."],
            post_hooks=[agent_as_judge_eval],
            db=db,
        )

        response = await research_team.arun("Explain quantum computing")
        print(response.content)

        # Query database for eval results
        print("Evaluation Results:")
        eval_runs = await db.get_eval_runs()
        if eval_runs:
            latest = eval_runs[-1]
            if latest.eval_data and "results" in latest.eval_data:
                result = latest.eval_data["results"][0]
                print(f"Score: {result.get('score', 'N/A')}/10")
                print(f"Status: {'PASSED' if result.get('passed') else 'FAILED'}")
                print(f"Reason: {result.get('reason', 'N/A')[:200]}...")


    if __name__ == "__main__":
        asyncio.run(main())

    ```
  </Step>

  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
        export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    ```bash theme={null}
    python agent_as_judge_team_post_hook_async.py
    ```
  </Step>
</Steps>