Manage automations

Enable, disable, trigger, and delete automations from your dashboard. Configure GitHub or GitLab triggers, schedules, context repos, and automerge.

Prerequisites

• A Mintlify project connected to a GitHub or GitLab repository
• For GitHub: the Mintlify GitHub App installed on every repository you plan to use in the automation
• For GitLab: a connected GitLab account (see GitLab setup below)

You can also create, list, and delete automations from the terminal with mint workflow. The CLI is useful for scripting and CI; the dashboard is the easiest way to configure and monitor automation runs.

Enable an automation

1. Open the Automations page in your dashboard.

2. Click the toggle beside an automation to enable it.

   

   If the automation can run with default settings, it activates immediately. Otherwise, the settings panel opens so you can fill in any required configurations.

   

3. If the settings panel opens, fill in the required fields.

4. Click Turn on automation.

To change settings for an active automation, click the settings button beside it. Use the toggle in the modal header to enable or disable the automation without leaving the settings view.

Configurations

Trigger

Each automation has a default trigger that controls when it runs. To change the trigger, select a different option in the settings panel.

• Content update: Runs whenever you push content to your project repository, including pull request merges and direct pushes.
• Code change: Runs when a pull request merges in a connected source code repository. You must specify at least one source repository.
• Custom schedule: Runs on a recurring schedule you define. Automations queue within 10 minutes of the scheduled time.

Update mode

Each automation has a default mode for how it makes updates: either directly merging changes into your content repository, or opening a pull request for review.

To require a review before the automation updates your content, select Require review in the settings panel.

For GitHub repositories, automatic updates require the Mintlify GitHub App to have bypass permissions on every ruleset targeting your deploy branch, including organization-level and repository-level rulesets. See Configure automerge for setup instructions.

For GitLab repositories, automerge uses the GitLab OAuth connection and requires at least the Maintainer role on each project.

Context repositories

For custom automations and some predefined automations, you can add context repositories—additional source code repositories the agent reads when the automation runs. This is useful when your automation prompt references code, APIs, or other content that lives outside your project repository.

You can add up to 10 context repositories per automation. For each GitHub repository, install the Mintlify GitHub App. Add repositories on the GitHub App settings page.

Integrations

For custom automations and the Update from code changes automation, you can enable connected agent integrations. The agent then pulls context from tools like Slack, Notion, or Linear when the automation runs.

To enable integrations for an automation, open its settings and select the integrations you want the agent to use in the Available integrations section. Only integrations already connected for your organization appear in the list. See Agent integrations for more information on connecting integrations.

Slack notifications

Send Slack messages to one or more channels when automations run.

To enable Slack notifications:

1. Install the Mintlify Slack app in your workspace.

2. Click Turn on Slack notifications on the Automations page of your dashboard.

   

3. Select one or more notification channels.

4. Click Save changes.

Once enabled, Mintlify posts to the selected channels when:

• An automation opens a pull request for review.
• An automation pull request has been waiting for review for three days.
• An automation merges a pull request, or fails to complete.

Instructions

Add optional instructions that append to the automation’s base prompt on every run. Use these to adjust the style, tone, or other project-specific behaviors without changing the core automation logic.

Target languages

When you enable the Translate content automation, select one or more languages to keep in sync with your source content.

• Mintlify reads the languages defined in your docs.json to identify your default language and preselects any already configured target languages.
• You must select at least one target language to save the automation.
• You cannot select the source language as a target.

You can add target languages at any time by opening the automation’s settings and editing the Translate to field.

GitLab setup

To use GitLab repositories in an automation, connect each project through the GitLab OAuth settings page. Connect every repository the automation touches—your documentation repository and any trigger or context repositories. You must have at least the Maintainer role on each project.

Automations require a paid GitLab tier. The agent uses short-lived project access tokens for repository access, which GitLab’s Free plan does not support.

Disable an automation

1. Open the Automations page in your dashboard.
2. Click the toggle beside an automation to disable it.

When you re-enable a scheduled automation or change its schedule, Mintlify recalculates the next run time from the current time. Disabled automations do not retain a pending run time.

Run an automation manually

You can trigger any enabled automation on demand without waiting for its next scheduled or event-based run.

1. Open the Automations page in your dashboard.
2. Click the run button beside the automation you want to start.

Manual runs use the automation’s current configuration, count toward your credit usage, and appear in the run history alongside scheduled runs.

View run history

Each automation keeps a log of past runs, including the status and a summary of changes made.

1. Open the Automation Runs page in your dashboard.

2. Use the dropdown menus to filter by specific automations or status.

   

Each run shows one of the following statuses:

• Queued: The run is waiting to start. Scheduled runs queue within 10 minutes of the scheduled time.
• In progress: The agent is actively working on the run.
• Succeeded: The agent finished the run. If the automation made changes, the run links to the resulting commit or pull request.
• Failed: The agent could not complete the run. Failed runs do not count toward your daily run limit.
• No changes: The agent finished the run but did not find anything to update.

Click an individual run to see its prompt, the files it read or changed, and any pull request it opened.

Continue a run in the editor

After an automation completes and creates changes on a branch, you can open those changes directly in the editor to review, refine, or publish them.

1. Open the Automations page in your dashboard.
2. Click View changes beside the workflow run you want to continue working on in the editor.

The editor opens to the automation’s branch with the agent panel already open. The agent panel shows each page the automation changed. Click any page to view changes made by the automation.

The editor agent has full context on what the automation did, including the automation’s prompt, a summary of the changes, and which pages the automation modified. Ask the agent to refine or extend the work without re-explaining the background.