Your team, your customers, and the AI agents of the world all depend on accurate, accessible knowledge.

Modern teams ship faster than documentation can keep up, and AI now depends on that documentation as much as humans do. The Mintlify agent and workflows closes that gap with a self-updating documentation engine grounded in your codebase.

Workflows run the agent automatically on a schedule or on a push to a repository. Each workflow defines a prompt for the agent and a trigger for when to run it.

When a workflow runs, the agent clones any specified repositories as context, follows the prompt, and either opens a pull request or pushes changes directly to your deployment branch.

You can select repositories for the agent to monitor and proactively identify documentation updates. Then, you’ll be able to:

1. Detect code changes that require documentation updates

Whenever you ship, no matter how big or small, the agent reviews the changed files and identifies suggestions for what needs to be updated and reflected in your docs.

2. Surface the updates

In the agent panel, you’ll see exactly which PRs introduced changes that may require documentation. This means no more guessing, no more hunting information, no more asking your teammates “who knows how this works?”

3. Generate documentation drafts

With full context of your codebase and your existing documentation structure and tone, the agent creates a draft that you can iterate on, refine, and generate a PR.

It keeps a human in the loop while automating your workflow, so you can stay ahead and publish docs as quickly as you ship products.

If you're ready to explore auto-updating documentation, get in touch for a demo.