> ## 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 work without an open chat

> Have your agent prepare recurring work that can run without an open chat.

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

## 1. Have your context ready

Identify the environment that will run the job, its workspace, schedule, expected output, and stopping conditions.

## 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 Prepare this Deepline task for unattended execution. First prove one foreground run in the intended environment and workspace. Save its run identity and review the result. Then propose the recurring entry point, credentials, overlap handling, usage controls, and recovery behavior. Explain where failures will be visible and how I can pause the work. Do not activate recurrence yet.
```

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 background environment has its own working authorization and preserves execution identity. A working interactive session alone does not prove unattended readiness.

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

The worker times out while the Play is running. Should its restart automatically submit the input again?

> **Show the answer**
>
> No. Observe the saved run ID first. A caller timeout does not prove that
> remote work stopped, and a new run can repeat work.

## Related guides

* [Deploy Plays with GitHub Actions](/docs/human/sdk-v2/github-deployments)
* [Call Plays](/docs/human/sdk-v2/calling-plays)
* [Production Play Integration](/docs/human/sdk-v2/production-integration)
* [Webhooks and schedules](/docs/human/sdk-v2/webhooks-and-schedules)


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