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

# Run a Play with your agent

> Ask your agent to start one reviewed Play and keep track of that run.

[Agent guide: CLI and SDK instructions →](/docs/sdk-v2/calling-plays)

## 1. Have your context ready

Know which Play and workspace you intend to use. Have a representative input and a budget for the pilot.

## 2. Ask your agent

Paste this into your agent, then provide your task and example inputs when it asks:

```deepline-prompt theme={null}
/deepline-gtm Inspect the Play I name and verify that my input fits. Explain what the run will do and its applicable usage before starting it. When I approve the pilot, start it once, save the returned run identity, and inspect that same run through completion. If a response is lost or polling stops, investigate the existing run before submitting another one.
```

Complete any requested sign-in yourself. Give the agent the missing information before approving execution. Provider-backed work can incur usage.

## 3. Review the result

The result belongs to the saved run and the intended input. A local wait ending does not prove that the run stopped.

Ask your agent:

```deepline-prompt theme={null}
/deepline-gtm Compare the result with the acceptance rule we agreed. Show the evidence for accepted and rejected outcomes, unresolved questions, and recorded Deepline usage where work ran. If work is still running or a response is uncertain, inspect the original saved execution before proposing another request. Explain the next decision I need to make.
```

Approve a larger job, recurring work, or external changes only after reviewing that decision.

## Check your understanding

What should you ask the agent to save after starting a Play?

> **Show the answer**
>
> Ask it to save the returned run identity and inspect that same run after an
> interruption. Do not start a replacement merely because a response was lost.

## Related guides

* [Production Play Integration](/docs/human/sdk-v2/production-integration)
* [Prebuilt Plays](/docs/human/sdk-v2/prebuilt-plays)
* [Run logs and events](/docs/sdk-v2/run-events)
* [HTTP and Python](/docs/human/sdk-v2/http-and-python)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.