> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-codex-docs-audit-20260719-0149.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Team Agent-as-Judge Evaluation

> Judge a researcher/writer Team response with binary AgentAsJudgeEval scoring persisted to SqliteDb.

Demonstrates response quality evaluation for team outputs.

```python agent_as_judge_team.py theme={null}
"""
Team Agent-as-Judge Evaluation
==============================

Demonstrates response quality evaluation for team outputs.
"""

from typing import Optional

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.eval.agent_as_judge import AgentAsJudgeEval, AgentAsJudgeResult
from agno.models.openai import OpenAIChat
from agno.team.team import Team

# ---------------------------------------------------------------------------
# Create Database
# ---------------------------------------------------------------------------
db = SqliteDb(db_file="tmp/agent_as_judge_team.db")

# ---------------------------------------------------------------------------
# Create Team
# ---------------------------------------------------------------------------
researcher = Agent(
    name="Researcher",
    role="Research and gather information",
    model=OpenAIChat(id="gpt-4o"),
)
writer = Agent(
    name="Writer",
    role="Write clear and concise summaries",
    model=OpenAIChat(id="gpt-4o"),
)
research_team = Team(
    name="Research Team",
    model=OpenAIChat("gpt-4o"),
    members=[researcher, writer],
    instructions=["First research the topic thoroughly, then write a clear summary."],
    db=db,
)

# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
evaluation = AgentAsJudgeEval(
    name="Team Response Quality",
    model=OpenAIChat(id="gpt-5.2"),
    criteria="Response should be well-researched, clear, and comprehensive with good flow",
    scoring_strategy="binary",
    db=db,
)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    response = research_team.run("Explain quantum computing")
    result: Optional[AgentAsJudgeResult] = evaluation.run(
        input="Explain quantum computing",
        output=str(response.content),
        print_results=True,
        print_summary=True,
    )
    assert result is not None, "Evaluation should return a result"

    print("Database Results:")
    eval_runs = db.get_eval_runs()
    print(f"Total evaluations stored: {len(eval_runs)}")
    if eval_runs:
        latest = eval_runs[-1]
        print(f"Eval ID: {latest.run_id}")
        print(f"Team: {research_team.name}")
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai sqlalchemy
    ```
  </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">
    Save the code above as `agent_as_judge_team.py`, then run:

    ```bash theme={null}
    python agent_as_judge_team.py
    ```
  </Step>
</Steps>

Full source: [cookbook/09\_evals/agent\_as\_judge/agent\_as\_judge\_team.py](https://github.com/agno-agi/agno/blob/v2.7.4/cookbook/09_evals/agent_as_judge/agent_as_judge_team.py)