> ## 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.

# Use Deepline with an agent

> Choose Claude Code, Claude Cowork, MCP, Hermes, or the Deepline GTM agent reference implementation.

[Human guide: work with your agent →](https://deepline.com/docs/human/use-with-an-agent.md)

> [!NOTE]
>
> Select an interface, authorize one workspace, and inspect a candidate workflow
> before executing it.

Use the interface that matches where your agent runs. Each option works with
the same Deepline Plays, Monitors, Database, integrations, and run history.

> **[Claude Code](https://deepline.com/docs/claude-plugins.md)**
>
> Install the Deepline plugin and Skills when Claude Code is where you work.

> **[Claude Cowork](https://deepline.com/docs/claude-cowork.md)**
>
> Use the Deepline plugin from Claude Desktop with Cowork.

> **[MCP](https://deepline.com/docs/mcp/setup.md)**
>
> Connect Deepline to ChatGPT Work, Claude Desktop, or another MCP client.

> **[Grok Bot](https://deepline.com/docs/grok-bot.md)**
>
> Run Deepline from xAI's desktop assistant using its computer access and
> skills.

> **[Hermes](https://github.com/getaero-io/deepline-gtm-agent/tree/master/hermes-agent-pack)**
>
> Run Deepline through the Hermes compatibility pack when Hermes is your
> operator interface.

> **[Build a custom agent](https://github.com/getaero-io/deepline-gtm-agent)**
>
> Start from the open-source Deepline GTM agent reference implementation for a
> Slack, REST, or web-chat agent backed by the Deepline API.

## Choose the right path

| If you need… | Start here |
| - | - |
| An agent in your coding workspace | [Claude Code](https://deepline.com/docs/claude-plugins.md) |
| An agent in Claude Desktop | [Claude Cowork](https://deepline.com/docs/claude-cowork.md) |
| Deepline inside an existing MCP client | [MCP setup](https://deepline.com/docs/mcp/setup.md) |
| Deepline in xAI's desktop assistant | [Grok Bot](https://deepline.com/docs/grok-bot.md) |
| Hermes as the operator interface | [Hermes agent pack](https://github.com/getaero-io/deepline-gtm-agent/tree/master/hermes-agent-pack) |
| A deployable agent you own | [Deepline GTM agent](https://github.com/getaero-io/deepline-gtm-agent) |

> [!NOTE]
>
> The custom-agent reference keeps Deepline responsible for provider routing,
> integrations, billing, Play execution, and run history. Your agent owns its
> interface, authentication, and user experience.

## Run a job with a Deepline skill

After installing through [Quickstart](https://deepline.com/docs/quickstart.md), use `deepline-gtm` for a GTM
request or choose a specialized entry from the [skill catalog](https://deepline.com/docs/features/claude-code-skills.md).

1. Define the output, format, evidence, and acceptance checks.
2. Inspect the input and preserve existing good data.
3. Search and describe the tools or Plays that may execute the job.
4. Run a small pilot.
5. Review coverage, evidence, failures, and the Deepline-facing spend estimate.
6. Approve the full run.
7. Export the result or save the accepted workflow as a reusable Play.

For durable code, schedules, and webhooks, use `deepline-gtm` with the
[Play authoring guide](https://deepline.com/docs/sdk-v2/plays.md) and `deepline plays --help`.

## Verify this task

Verify authorization in the environment that will execute commands. Distinguish installed skills from effective workspace access.

Ask your agent to explain a failed check before repeating work or expanding the scope.


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