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

# Batch Agent-as-Judge Evaluation

> Judge three pre-supplied customer-service cases with binary scoring, persist the evaluation runs in SqliteDb, and report the result pass rate.

Demonstrates evaluating multiple cases in one run.

<Warning>
  This example reads `eval_runs[-1]`, but `SqliteDb.get_eval_runs()` returns the newest evaluation first. Replace the index before running so the reported ID belongs to the evaluation that just completed.
</Warning>

```python agent_as_judge_batch.py theme={null}
"""
Batch Agent-as-Judge Evaluation
===============================

Demonstrates evaluating multiple cases in one run.
"""

from agno.db.sqlite import SqliteDb
from agno.eval.agent_as_judge import AgentAsJudgeEval

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

# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
evaluation = AgentAsJudgeEval(
    name="Customer Service Quality",
    criteria="Response should be empathetic, professional, and helpful",
    scoring_strategy="binary",
    db=db,
)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    result = evaluation.run(
        cases=[
            {
                "input": "My order is delayed and I'm very upset!",
                "output": "I sincerely apologize for the delay. I understand how frustrating this must be. Let me check your order status right away and see how we can make this right for you.",
            },
            {
                "input": "Can you help me with a refund?",
                "output": "Of course! I'd be happy to help with your refund. Could you please provide your order number so I can process this quickly for you?",
            },
            {
                "input": "Your product is terrible!",
                "output": "I'm sorry to hear you're disappointed. Your feedback is valuable to us. Could you share more details about what went wrong so we can improve?",
            },
        ],
        print_results=True,
        print_summary=True,
    )

    print(f"Pass rate: {result.pass_rate:.1f}%")
    print(f"Passed: {sum(1 for r in result.results if r.passed)}/{len(result.results)}")

    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"Cases evaluated: {len(result.results)}")
```

## 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 API keys">
    <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="Read the latest evaluation">
    Replace `latest = eval_runs[-1]` with `latest = eval_runs[0]` in the saved file.
  </Step>

  <Step title="Run the example">
    Save the code above as `agent_as_judge_batch.py`, then run:

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

Full source: [cookbook/09\_evals/agent\_as\_judge/agent\_as\_judge\_batch.py](https://github.com/agno-agi/agno/blob/main/cookbook/09_evals/agent_as_judge/agent_as_judge_batch.py)