> ## 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.

# Choose an implementation with your agent

> Ask your agent to choose a maintained implementation for your task.

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

## 1. Have your context ready

Describe the result, input, caller environment, and destination. An example’s name does not establish that its input fits.

## 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 Find the maintained Deepline example closest to my task. Read its actual input, output, and caller contract. Explain what can be reused and what must change for my application or file. Preserve execution identity and approval boundaries. Show the proposed adaptation and a representative test before starting provider work or deploying it.
```

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 agent identifies the source example and explains its differences from your task. The adapted workflow has a defined input and a result you can inspect.

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

Does an example file name prove it accepts your input schema?

> **Show the answer**
>
> No. Read the source and inspected contract. An example is not a universal
> adapter for arbitrary fields.

## Related guides

* [Batch CSV enrichment](/docs/human/sdk-v2/batch-csv)
* [Prebuilt Plays](/docs/human/sdk-v2/prebuilt-plays)
* [Write Plays](/docs/human/sdk-v2/plays)
* [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.