1
Add the following code to your Python file
agent_as_judge_batch.py
from agno.db.sqlite import SqliteDb
from agno.eval.agent_as_judge import AgentAsJudgeEval
# Setup database to persist eval results
db = SqliteDb(db_file="tmp/agent_as_judge_batch.db")
evaluation = AgentAsJudgeEval(
name="Customer Service Quality",
criteria="Response should be empathetic, professional, and helpful",
scoring_strategy="binary", # PASS/FAIL for each case
db=db,
)
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(f"Pass rate: {result.pass_rate:.1f}%")
print(f"Passed: {sum(1 for r in result.results if r.passed)}/{len(result.results)}")
2
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
3
Install dependencies
uv pip install -U agno openai
4
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
5
Run the example
python agent_as_judge_batch.py