Embeddable AI agents

Your documents, working as an assistant.
Ship it anywhere with one snippet.

Blueprint indexes your files, PDFs, and web pages, connects the tools you need, and exposes a chat agent you can publish to any page — as a self-contained snippet that talks to your own API.

· Paragraph chunking· RAPTOR retrieval· MCP tools· Open endpoints

No agent to demo yet.

Create one in the builder and this panel goes live.

Open builder

01 · Capabilities

One agent, everything it needs to be useful.

Knowledge you can trust

Documents are split into clean paragraphs and indexed for retrieval. Every hit knows which source it came from, and answers are grounded in those passages.

Tools you can wire in

Connect file, database, and third-party servers over MCP. Tools arrive namespaced by server, and you enable them per agent — no code changes required.

An embed that ships anywhere

One self-contained snippet, no framework and no dependencies, served by open CORS-enabled endpoints. Paste it into any site, app, or admin panel.

02 · Live demo

Live, in this page.

The bubble below is the same self-contained snippet you'll copy from the builder's Deploy step — rendered here, shadow DOM and all.

No agent to demo yet.

Create one in the builder and this panel goes live.

Open builder

03 · How retrieval works

How answers stay grounded.

AIngest

Text, markdown, source code, PDFs, and web pages are read and normalized into clean paragraphs.

extract_paragraphs()

BIndex

Paragraphs are embedded and organized into a summary tree, so related passages cluster and retrieve together.

RAPTOR indexer

CRetrieve & answer

The best passages are gathered with their source documents and passed to the model, so answers carry citations.

[1](doc A) · [2](doc B)

Citations with source links Answers cite their sources Clean paragraph chunking Upload via API or drag & drop

Start building.

Create an agent, add your knowledge, and publish it anywhere.

Open the builder
Blueprint · Agents for your content status: operational