> ## Documentation Index
> Fetch the complete documentation index at: https://spacesail.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Simple Agent Evals

> Learn how to evaluate your Agno Agents and Teams across three key dimensions - accuracy (using LLM-as-a-judge), performance (runtime and memory), and reliability (tool calls).

**Evals** is a way to measure the quality of your Agents and Teams. Agno provides 3 dimensions for evaluating Agents:

## Evaluation Dimensions

<CardGroup cols={3}>
  <Card title="Accuracy" icon="bullseye" href="/concepts/evals/accuracy">
    The accuracy of the Agent's response using LLM-as-a-judge methodology.
  </Card>

  <Card title="Performance" icon="stopwatch" href="/concepts/evals/performance">
    The performance of the Agent's response, including latency and memory footprint.
  </Card>

  <Card title="Reliability" icon="shield-check" href="/concepts/evals/reliability">
    The reliability of the Agent's response, including tool calls and error handling.
  </Card>
</CardGroup>

## Quick Start

Here's a simple example of running an accuracy evaluation:

```python quick_eval.py theme={null}
from typing import Optional
from agno.agent import Agent
from agno.eval.accuracy import AccuracyEval, AccuracyResult
from agno.models.openai import OpenAIChat
from agno.tools.calculator import CalculatorTools

# Create an evaluation
evaluation = AccuracyEval(
    model=OpenAIChat(id="o4-mini"),
    agent=Agent(model=OpenAIChat(id="gpt-5-mini"), tools=[CalculatorTools()]),
    input="What is 10*5 then to the power of 2? do it step by step",
    expected_output="2500",
    additional_guidelines="Agent output should include the steps and the final answer.",
)

# Run the evaluation
result: Optional[AccuracyResult] = evaluation.run(print_results=True)
assert result is not None and result.avg_score >= 8
```

## Best Practices

* **Start Simple:** Begin with basic accuracy tests before moving to complex performance and reliability evaluations
* **Use Multiple Test Cases:** Don't rely on a single test case - create comprehensive test suites
* **Track Over Time:** Monitor your eval results as you make changes to your agents
* **Combine Dimensions:** Use all three evaluation dimensions for a complete picture of agent quality

## Next Steps

Dive deeper into each evaluation dimension:

1. **[Accuracy Evals](/concepts/evals/accuracy)** - Learn LLM-as-a-judge techniques and multiple test case strategies
2. **[Performance Evals](/concepts/evals/performance)** - Measure latency, memory usage, and compare different configurations
3. **[Reliability Evals](/concepts/evals/reliability)** - Test tool calls, error handling, and rate limiting behavior