Use case

AI Agents for Documentation Sites

AIML.chat adds an AI agent to your documentation site that answers from your own docs, README, and code — returning the exact snippet, citing the page, and telling you which questions your docs don't answer well. Search finds pages; an agent gives answers.

AIML.chat adds an AI agent to your documentation site that answers from your own docs, README, and code — returning the exact snippet, citing the page, and telling you which questions your docs don't answer well. Search finds pages; an agent gives answers.

Documentation search returns a list of pages and leaves the reader to dig. Developers want the specific flag, endpoint, or config that solves their problem — now. A technical agent indexes your docs, API reference, and GitHub repository, then answers precisely, pulling the relevant snippet and linking to the source page so the reader can verify it. It never invents an API that doesn't exist: when the answer isn't in your content, it says so and offers to escalate.

Turn support load into a docs backlog

Every question your agent can't answer well is a gap in your documentation. The analytics dashboard surfaces those unanswered questions, ranked by frequency, so your next docs sprint writes exactly what readers are asking for. Re-crawl on a schedule and the agent updates itself as your docs change — no stale answers. Connect issue tracking over MCP and the agent can even open a documentation issue, with human approval on every write.

Built for docs tooling

It works with whatever you publish from — Docusaurus, MkDocs, VitePress, GitBook, Mintlify, and more — because it indexes the rendered site or your repo directly. Embed one script tag and it's live. Compare approaches below, then read the technical agent page for how it returns code and config.

ApproachAnswers fromReturns snippetsFinds doc gaps
Built-in docs searchA page indexNoNo
AIML.chat agentYour docs, repo & codeYes, citedYes, ranked
Generic site chatbotA scripted treeNoNo
Does it work with my docs framework?+

Yes — it indexes the rendered site or your GitHub repo, so Docusaurus, MkDocs, VitePress, GitBook, Mintlify, and others all work.

Will it return real code snippets?+

Yes. It pulls the relevant snippet from your indexed content and cites the page it came from, so readers can verify it.

Is there a free plan?+

Yes — 100 messages a month and one website on the free tier. See pricing for higher limits.

Add AI chat to your site

Free plan · No credit card · 5 minutes