Skip to main content
"""
Asynchronous Reliability Evaluation
==================================

Demonstrates running reliability checks with asynchronous evaluation.
"""

import asyncio
from typing import Optional

from agno.agent import Agent
from agno.eval.reliability import ReliabilityEval, ReliabilityResult
from agno.models.openai import OpenAIChat
from agno.run.agent import RunOutput
from agno.tools.calculator import CalculatorTools


# ---------------------------------------------------------------------------
# Create Evaluation Function
# ---------------------------------------------------------------------------
def factorial():
    agent = Agent(
        model=OpenAIChat(id="gpt-5.2"),
        tools=[CalculatorTools()],
    )
    response: RunOutput = agent.run("What is 10!?")
    evaluation = ReliabilityEval(
        agent_response=response,
        expected_tool_calls=["factorial"],
    )

    # Run the evaluation calling the arun method.
    result: Optional[ReliabilityResult] = asyncio.run(
        evaluation.arun(print_results=True)
    )
    if result:
        result.assert_passed()


# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    factorial()

​
Run the Example

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

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

python reliability_async.py