> ## 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.

# Prebuilt Workflows

> Find, inspect, run, and compose Deepline-maintained GTM workflows. Use it to pilot on a few rows, verify the output, and scale the workflow safely.

Job: use a working GTM workflow without designing the waterfall yourself.

A prebuilt play is a Deepline-maintained workflow. It is not a raw provider tool.

## Find the right play

```bash theme={null}
deepline plays search email --json
```

Look for:

| Field         | Why it matters                         |
| ------------- | -------------------------------------- |
| `name`        | What you run                           |
| `origin`      | `prebuilt` means Deepline-maintained   |
| `inputSchema` | What your CSV or API call must provide |
| `runCommand`  | Copyable CLI starter                   |

## Inspect it

```bash theme={null}
deepline plays describe prebuilt/person-linkedin-to-email --json
```

Ask: “Do I have the required inputs?” not “Which provider should I call?”

## Pilot one record

Use the same input shape everywhere:

```bash theme={null}
deepline plays run prebuilt/person-linkedin-to-email \
  --input '{"linkedin_url":"https://www.linkedin.com/in/example-person/"}' \
  --watch
```

If the pilot output looks right, scale through a custom play or CSV workflow.

## Compose it inside your own play

Inside a custom workflow, call the prebuilt workflow by name only when the play
compiler can statically resolve that child play in your workspace. For most
users, start by running and inspecting the prebuilt directly:

```bash theme={null}
deepline plays describe prebuilt/person-linkedin-to-email --json
deepline plays run prebuilt/person-linkedin-to-email \
  --input '{"linkedin_url":"https://www.linkedin.com/in/example-person/"}' \
  --watch
```

<Warning>
  Do not call prebuilt plays with `deepline tools execute` or
  `ctx.tools.execute`. Use `deepline plays run` or `ctx.runPlay`.
</Warning>