Dewey – Ingest docs, search semantically, get cited AI answers
Structure-aware chunking beats flat embeddings for accurate multi-hop research and citations.

Yet another RAG platform when Cursor and Sourcegraph already own this space.
Technical support teams and documentation maintainers
Sourcegraph Cody · Cursor · GitBook AI
Structure-aware chunking beats flat embeddings for accurate multi-hop research and citations.
First open-source AEO monitor tracking AI citations across ChatGPT, Gemini, and Claude.
Git-style branching for docs that agents can actually read via MCP.
It bundles knowledge base articles, a public roadmap with voting, structured feedback boards, release notes and API reference into one branded portal — exactly the convenience product teams ask for when they're juggling GitHub issues, Canny and a separate docs site. The admin UI in the screenshot (analytics, content counts, role controls) reads clean and usable, but this lives in a crowded field; success will depend on smooth imports, strong integrations and demonstrable SEO/search benefits.
Statute citations per clause beat LegalZoom's generic templates.
This is a pragmatic, solo-built product that actually does the useful bits: it ingests help files, transcripts and even extracted error messages into a curated knowledge base and wires that to an Anthropic-backed chatbot with a demo you can drop on your site. Clever and focused for three-person shops that can't justify Zendesk, but the approach isn't novel in the broader market — I'd want clearer answers on integrations, privacy and scaling before trusting it for real-world support volume.