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

# Release Autopilot

**Developer**

**Federal docs**

> [!CAUTION]
>
> **Release Autopilot package features are not available in federal environments**
>
> To learn more, read [LaunchDarkly in federal environments](https://launchdarkly.com/docs/home/infrastructure/federal).

**EU docs**

> [!CAUTION]
>
> **Release Autopilot package features are not available in the LaunchDarkly European Union (EU) instance**
>
> To learn more, read [LaunchDarkly in the European Union (EU)](https://launchdarkly.com/docs/home/infrastructure/eu.md).

> [!NOTE]
>
> **Release Autopilot is available to customers on select plans**
>
> Release Autopilot is only available to customers on certain plans. To learn more, [read about our pricing](https://launchdarkly.com/pricing/) or [contact Sales](https://launchdarkly.com/contact-sales/).

This topic explains what Release Autopilot is, how it moves a change from pull request to flag cleanup, and where you can use each of its features.

Release Autopilot is a set of LaunchDarkly capabilities that makes a feature flag and a safe release the default for every change, whether humans or agents write the code. It reviews each change, wraps risky ones in a flag, releases them one environment at a time, and removes the flag when you no longer need it.

Each capability works on its own, or you can connect them into one flow.

Release Autopilot helps when:

* Your team merges changes faster than your release process can apply controls to them.
* Engineers act as manual reviewers for every release, which decreases the velocity of changes shipped.
* Creating, progressing, and cleaning up a flag for every change is too manual a process for the volume at which agents produce code.

## Prerequisites

Before you use Release Autopilot, you need:

* The Release Autopilot product offering.
* The Admin or Owner role, or a custom role that allows the Release Autopilot actions. To learn which actions, read the [Release Autopilot setup prerequisites](https://launchdarkly.com/docs/home/release-autopilot/setup.md#prerequisites).
* A GitHub account and private repositories, if you use the LaunchDarkly GitHub app.
* Access to an AI model, either through your own model provider key or through LaunchDarkly inference.

## How Release Autopilot works

![The five stages of Release Autopilot in order: classify, flag, release, clean up, and archive.](https://mintcdn.com/launchdarkly/YSbyl8ZI0zDxkGBR/images/__not_from_LD_app_UI/release-autopilot-diagram.png?fit=max\&auto=format\&n=YSbyl8ZI0zDxkGBR\&q=85\&s=317079b2b0b088df09a7f5c97b65fb57)

A change moves through Release Autopilot in five stages:

1. **Auto-classification.** Reviews a pull request when it's marked ready for review and recommends a flag and a release plan.
2. **Auto-flag.** After you approve, creates the flag and wraps the change in it, keeping the flag off for customers until the release starts.
3. **Auto-release.** Starts each configured environment according to its trigger and progresses environments through the release based on the supported execution mode.
4. **Auto-cleanup.** Opens a pull request that removes the flag from your code once it passes your lifecycle checks.
5. **Auto-archival.** After cleanup, archives the flag automatically or submits an approval request to do so, depending on the project’s auto-archive settings.

## Features and where to use them

The following table describes each Release Autopilot feature and where you can use it:

<table>
  <thead>
    <tr>
      <th>Feature</th>
      <th>What it does</th>
      <th>Where you use it</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>[Auto-classification](https://launchdarkly.com/docs/home/release-autopilot/autoclassification.md)</td>
      <td>Recommends a flag and a release plan for each pull request.</td>
      <td>GitHub app, agent skills</td>
    </tr>

    <tr>
      <td>[Auto-flag](https://launchdarkly.com/docs/home/release-autopilot/autoflag.md)</td>
      <td>Creates the flag and wraps the change in it.</td>
      <td>GitHub app, agent skills</td>
    </tr>

    <tr>
      <td>[Auto-release](https://launchdarkly.com/docs/home/release-autopilot/autorelease.md)</td>
      <td>Starts the release after deploy and progresses it through your environments in order.</td>
      <td>LaunchDarkly, Releases API, MCP server, CLI, agent skills</td>
    </tr>

    <tr>
      <td>Release tab and flag overview</td>
      <td>Shows the release plan for a flag, lets you pause and unpause a release, and links to the pull request.</td>
      <td>LaunchDarkly</td>
    </tr>

    <tr>
      <td>[Releases page](https://launchdarkly.com/docs/home/release-autopilot/releases-page.md)</td>
      <td>Shows every release in one view.</td>
      <td>LaunchDarkly</td>
    </tr>

    <tr>
      <td>[Auto-cleanup](https://launchdarkly.com/docs/home/release-autopilot/autocleanup.md)</td>
      <td>Opens a pull request that removes the flag from your code.</td>
      <td>GitHub app, LaunchDarkly, agent skills</td>
    </tr>

    <tr>
      <td>[Auto-archival](https://launchdarkly.com/docs/home/release-autopilot/autocleanup.md)</td>
      <td>Archives the flag after it passes your lifecycle checks.</td>
      <td>LaunchDarkly</td>
    </tr>

    <tr>
      <td>[Agent skills](https://launchdarkly.com/docs/home/release-autopilot/agent-skills.md)</td>
      <td>Runs the same steps from your editor, before you open a pull request.</td>
      <td>Claude Code, Cursor, and other agents</td>
    </tr>
  </tbody>
</table>

You can use Release Autopilot in three places:

* **In the pull request.** The LaunchDarkly GitHub app comments on each pull request and responds to `@launchdarkly` commands. To learn which commands you can use, read the [Release Autopilot FAQ](https://launchdarkly.com/docs/home/release-autopilot/faq.md).
* **In LaunchDarkly.** Review a flag's release on its **Release** tab, and manage lifecycle settings and Release Autopilot settings from your project.
* **In your editor or agent.** Use agent skills, the LaunchDarkly MCP server, or the CLI to run the same steps without leaving your workflow.

## Supported configurations

Release Autopilot currently supports the following configurations:

* The LaunchDarkly GitHub app works only with private GitHub repositories.
* Each repository maps to one project, and each pull request maps to one or more flags.
* You approve each flag and release plan before Release Autopilot creates them.
* Release Autopilot bypasses approval workflows.

## Next steps

> [card] [Set up Release Autopilot](https://launchdarkly.com/docs/home/release-autopilot/setup.md)
>
> Install the GitHub app, map repositories to projects, and opt in to each capability.

> [card] [Release Autopilot onboarding skill](https://launchdarkly.com/docs/home/release-autopilot/agent-skills.md#skills-by-task)
>
> Review the onboarding skill for Release Autopilot.

> [card] [Release Autopilot agent skills](https://launchdarkly.com/docs/home/release-autopilot/agent-skills.md)
>
> Review available agent skills.

> [card] [Release Autopilot FAQ](https://launchdarkly.com/docs/home/release-autopilot/faq.md)
>
> Find pull request commands and answers to common questions.
