Skip to content

docs: explain how automations fit with the agent and CLI #6738

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
mintlify wants to merge 1 commit into from
Closed

docs: explain how automations fit with the agent and CLI #6738

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions automations/index.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,16 @@ Automations run the agent automatically on a schedule, in response to pushes to

When an automation runs, the agent reads your project content and any connected repositories, then follows the prompt to make updates.

## How automations fit with the agent and CLI

Automations, the [agent](/agent), and the [`mint`](/cli/commands) CLI all run the same underlying agent, but you reach for them in different situations:

* **[Agent](/agent)**: Interactive. You send a prompt from the dashboard, editor, GitHub, or Slack when you want the agent to work on something right now. Best for one-off writing and updates that need a human in the loop from the start.
* **Automations**: Unattended. The agent runs on your behalf on a trigger you configure—a schedule, a push, or an integration event—without anyone kicking it off each time. Best for recurring maintenance work like translations, changelogs, or keeping content in sync with source code.
* **[`mint automations`](/cli/commands#mint-automations) CLI**: Scripted. Create, list, run, and delete the same automations from your terminal so they can live in CI pipelines, release scripts, or local tooling. The dashboard remains the easiest way to configure and monitor runs.

You can mix all three on the same project. For example, use an automation to keep translations in sync on every merge, use the CLI to trigger a changelog run from your release pipeline, and use the agent interactively when you need to write a new guide.

<Tip>
Use automations that run on a schedule for recurring tasks, like publishing changelogs or improving content based on users' conversations with the [assistant](/assistant).

Expand Down