Add a team of AI agents to your Next.js app — a support agent grounded in your content that answers with cited sources and can reach your tools via MCP, asking before it changes anything. Next.js makes embedding a one-component job.
What your visitors get
A visitor with a question gets an instant, cited answer pulled from your own 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 source page, so trust stays high. It also captures a lead when it can't fully answer, so you never lose a visitor, and the analytics surface the questions your content doesn't yet cover.
Add it in three steps
- 1Create a website in AIML.chat and point the crawler at your app's URL (or connect its GitHub repo). It indexes and embeds your public pages automatically.
- 2Add the embed with the
Scriptcomponent fromnext/script. In the App Router, place it in the rootapp/layout.tsx; in the Pages Router, add it to a custom_appor_document. - 3Deploy. The widget appears site-wide, themed to match, and stays current as you re-crawl.
Because the widget is vanilla JS under 30KB gzipped and loads with strategy="afterInteractive", it won't hurt your Core Web Vitals. As your content changes, a re-crawl — manual, scheduled, or via the GitHub Action on every push — keeps answers accurate. For docs-specific Next.js setups, see the Nextra guide.
How do I embed it in Next.js?+
Use the Script component from next/script in your root app/layout.tsx (App Router) or a custom _app/_document (Pages Router).
Will it hurt performance?+
No. The widget is under 30KB gzipped and loads after interactive, so it stays out of your critical path.
Is there a free plan?+
Yes — 100 messages a month and one website on the free tier. See pricing for higher limits.