> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-service-account.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Evals

> Lock in agent behavior with regression tests.

Next, let's lock in our agent behavior with evals.

Evals are regression tests for your agents. It's the same prompts and the same agents, run on a schedule, so you can see when behavior drifts.

When we run `/improve-agent`, we're looking for out-of-distribution improvements. Evals make sure in-distribution cases continue to pass. The two work together.

## Cases

Cases live in `evals/cases.py`. Each case sends one input to an agent and (optionally) checks two things:

* **judge**: `AgentAsJudgeEval` scores the response against `criteria` (binary pass/fail) using an LLM.
* **reliability**: `ReliabilityEval` checks which tools fired against `expected_tool_calls`.

A case looks like this:

```python evals/cases.py theme={null}
CASES: tuple[Case, ...] = (
    Case(
        name="web_search_recent_anthropic_research",
        agent=web_search,
        input="What did Anthropic publish about agent research recently?",
        tags=("live",),
        timeout_seconds=120,
        criteria=(
            "Answers the question by citing at least one real Anthropic URL "
            "(anthropic.com domain). The response is grounded in fetched content "
            "rather than refusing to answer."
        ),
        expected_tool_calls=(_WEB_SEARCH_TOOL,),
    ),
    # add more cases here
)
```

A case can use either check or both. If both are set, the agent runs once and feeds the same response into both.

Add tags to group your cases into suites. The template comes with three suites: `smoke`, `release`, and `live`. This case is tagged `live` because its answer depends on the open web.

## Run the suite

<Steps>
  <Step title="Create a virtual environment">
    The eval suite runs on the host and needs a local virtual environment:

    ```bash theme={null}
    ./scripts/venv_setup.sh
    ```

    Activate it:

    ```bash theme={null}
    source .venv/bin/activate
    ```
  </Step>

  <Step title="Run the eval suite">
    ```bash theme={null}
    python -m evals --tag smoke    # fast suite
    python -m evals                # full suite
    ```

    Other options:

    ```bash theme={null}
    python -m evals -v             # stream the agent run with full panels
    python -m evals --name <case>  # single case while iterating
    ```
  </Step>
</Steps>

Each case prints the response, the judge verdict, and the reliability verdict. The run ends with an `Eval Summary` table.

Results write to Postgres via `eval_db`. The eval history shows up on [os.agno.com](https://os.agno.com) alongside your sessions and traces, so you can see when a case started failing and what changed.

## Diagnose failures with Claude Code

Open Claude Code and run:

```
/eval-and-improve
```

Claude runs the suite, triages every failure (bad criteria, real regression, flaky LLM judge), and proposes in-scope fixes. It edits the agent or the case and re-runs until the suite is green.

## When to run evals

| Trigger                               | Frequency       |
| ------------------------------------- | --------------- |
| Before deploying a change to an agent | Every time      |
| As part of CI                         | Every PR        |
| Against production                    | On a daily cron |
| After bumping a model version         | Every time      |

The production cron is the most valuable one, and the template ships it as the `run_evals` workflow. Set `ENABLE_SCHEDULED_EVALS=True` to run the `smoke`-tagged cases daily. See [scheduling](/features/scheduling) for the cron API.

## What good cases look like

* **Specific.** "Returns a JSON object with `ticker` and `price`" beats "Returns the right answer".
* **Stable.** Avoid prompts whose correct answer changes daily. Use phrasing like "describes a real, recent..." instead of locking in a specific result.
* **Scoped to one behavior.** One case per behavior makes failures easy to read.
* **Anchored to tools.** `expected_tool_calls` catches the failure mode where the agent confidently makes things up instead of calling a tool.

## Next

[Next steps →](/agent-platform/next-steps)