Watch Knowledge Stack

Five short videos. Each one is under three minutes and shows a single capability end-to-end on real data. No slides.

​

90-second product tour

The fastest way to understand what Knowledge Stack does — ingest a folder of PDFs, run a permission-scoped search, ask a question, and follow a citation back to the source page.

​

Ingestion pipeline in action

Watch a 200-page report flow through the Temporal-backed ingestion worker — conversion, chunking, embedding, and the resulting tree of PathPart nodes you can search against. Read the deep dive: Ingestion Pipeline · Temporal workflow · Chunk handling.

​

Plug into your agent framework

Same MCP server, three different hosts — LangGraph, the OpenAI Agents SDK, and Claude Desktop — each running a permission-scoped retrieval call against the same Knowledge Stack tenant. More patterns: MCP server · Cookbook flagships.

​

Citations that survive an audit

Every assistant claim links back to a chunk UUID, a page number, and a bounding box. Click a citation, jump to the highlighted region of the original PDF. How it works: Citations · Threads & streaming.

​

Permission-aware retrieval

Two users. Same query. Different results — by construction, not by post-filtering. We show how path-level grants flow through search and chat. Concept docs: Path system · Authorization.

---

​

Where to next