Binary Agent as Judge

Binary pass/fail evaluation without numeric scoring

This example demonstrates binary PASS/FAIL evaluation mode without numeric scoring.

1. Add the following code to your Python file

   agent_as_judge_binary.py

   from agno.agent import Agent
   from agno.db.sqlite import SqliteDb
   from agno.eval.agent_as_judge import AgentAsJudgeEval
   from agno.models.openai import OpenAIResponses
   
   # Setup database to persist eval results
   db = SqliteDb(db_file="tmp/agent_as_judge_binary.db")
   
   agent = Agent(
       model=OpenAIResponses(id="gpt-5.2"),
       instructions="You are a customer service agent. Respond professionally.",
       db=db,
   )
   
   response = agent.run("I need help with my account")
   
   evaluation = AgentAsJudgeEval(
       name="Professional Tone Check",
       criteria="Response must maintain professional tone without informal language or slang",
       db=db,
   )
   
   result = evaluation.run(
       input="I need help with my account",
       output=str(response.content),
       print_results=True,
       print_summary=True,
   )
   
   print(f"Result: {'PASSED' if result.results[0].passed else 'FAILED'}")
   
   
2. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
3. Install dependencies

   uv pip install -U agno openai
   
4. Export your OpenAI API key

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   
5. Run the example

   python agent_as_judge_binary.py