Add a team of AI agents to your Mintlify docs — a support agent grounded in your content that answers with cited sources and can reach your tools via MCP, asking before it changes anything. Mintlify's clean config makes embedding quick.
What your readers get
A reader who's stuck gets an instant, cited answer pulled from your own Mintlify pages rather than a generic guess. Behind the widget, AIML.chat runs a Support agent grounded in your content and tool-calling agents that act through the Model Context Protocol (MCP), with human write-confirm on anything that changes data. Every answer links to the exact page, and the analytics show which questions your docs don't yet answer. It also captures a lead when it can't fully answer, so you never lose a visitor — and you can adopt its generated FAQ suggestions as starter prompts that greet readers the moment the widget opens.
Add it in three steps
- 1Create a website in AIML.chat and point the crawler at your Mintlify docs URL (or connect the GitHub repo your MDX lives in). It indexes every page automatically.
- 2Add the embed snippet through Mintlify's custom scripts configuration (the
head/custom-script option in yourdocs.json). - 3Deploy. The assistant appears across your docs, themed to match, and stays current as you re-crawl.
Because the widget is vanilla JS under 30KB gzipped, it loads cleanly inside Mintlify's fast theme. As your docs change, a re-crawl — manual, scheduled, or via the GitHub Action on every push — keeps answers accurate. For similar platforms, see the ReadMe and GitBook guides.
How do I embed it in Mintlify?+
Add the snippet via Mintlify's custom scripts option in your docs.json, and it loads across your docs.
Will it stay in sync as my docs change?+
Yes. Re-crawl on demand, on a schedule, or automatically on every push with the GitHub Action.
Is there a free plan?+
Yes — 100 messages a month and one website on the free tier. See pricing for higher limits.