Skip to main content
"""
Custom Evaluator Agent-as-Judge Evaluation
==========================================

Demonstrates using a custom evaluator agent for judging.
"""

from agno.agent import Agent
from agno.eval.agent_as_judge import AgentAsJudgeEval
from agno.models.openai import OpenAIChat

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    instructions="Explain technical concepts simply.",
)

# ---------------------------------------------------------------------------
# Create Evaluator Agent
# ---------------------------------------------------------------------------
custom_evaluator = Agent(
    model=OpenAIChat(id="gpt-4o"),
    description="Strict technical evaluator",
    instructions="You are a strict evaluator. Only give high scores to exceptionally clear and accurate explanations.",
)

# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
evaluation = AgentAsJudgeEval(
    name="Technical Accuracy",
    criteria="Explanation must be technically accurate and comprehensive",
    scoring_strategy="numeric",
    threshold=8,
    evaluator_agent=custom_evaluator,
)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    response = agent.run("What is machine learning?")
    result = evaluation.run(
        input="What is machine learning?",
        output=str(response.content),
        print_results=True,
    )
    print(f"Score: {result.results[0].score}/10")
    print(f"Passed: {result.results[0].passed}")

​
Run the Example

# Clone and setup repo
git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/09_evals/agent_as_judge

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python agent_as_judge_custom_evaluator.py