# AI agent acceptance checks: prove the task finished

Define the observable outcome outside the agent transcript. Check the saved artifact or permitted state change, then decide where a failed check goes. A run status can describe execution without establishing that the requested work is useful.

## Worked example

For a report task, check that the file exists, opens and contains the required sections. For a record update, check the allowed fields on the intended record. Keep a failure owner and a recovery step in the same worksheet.

## Copyable prompt

```text
Turn [WORKFLOW] into an acceptance contract. Include expected artifact or state, a deterministic validation step where possible, allowed side effects, timeout, failure owner and recovery action. Identify what can be verified automatically and what needs human review. A completed run status alone must not count as acceptance. Return a table with blank fields clearly marked.
```

## Checklist

- Define the expected artifact or state.
- Verify the result independently of the status message.
- Name a failure owner and recovery action.
- Record what still needs human judgment.

## Further reading

[Anthropic: building effective agents](https://www.anthropic.com/engineering/building-effective-agents)