evaluator_agent.py
"""
Accuracy Evaluation with Custom Evaluator Agent
================================================
Demonstrates accuracy evaluation using a custom evaluator agent.
"""
from typing import Optional
from agno.agent import Agent
from agno.eval.accuracy import AccuracyAgentResponse, AccuracyEval, AccuracyResult
from agno.models.openai import OpenAIChat
from agno.tools.calculator import CalculatorTools
# ---------------------------------------------------------------------------
# Create Evaluator Agent
# ---------------------------------------------------------------------------
evaluator_agent = Agent(
model=OpenAIChat(id="gpt-5"),
output_schema=AccuracyAgentResponse,
)
# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
evaluation = AccuracyEval(
model=OpenAIChat(id="o4-mini"),
agent=Agent(model=OpenAIChat(id="gpt-5.2"), tools=[CalculatorTools()]),
input="What is 10*5 then to the power of 2? do it step by step",
expected_output="2500",
evaluator_agent=evaluator_agent,
additional_guidelines="Agent output should include the steps and the final answer.",
)
# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
result: Optional[AccuracyResult] = evaluation.run(print_results=True)
assert result is not None and result.avg_score >= 8
Run the Example
1
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
2
Install dependencies
uv pip install -U agno openai
3
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
4
Run the example
Save the code above as
evaluator_agent.py, then run:python evaluator_agent.py