LangChain's 'knowledge factory': turning company know-how into agent learning loops
hwchase17 · x · 2026-11-22
LangChain CEO Harrison Chase shares a new article, "How to build a knowledge factory," arguing the missing piece for enterprise AI isn't better models or more context — it's better knowledge of how the company actually works and its standards. RT author Tanish Sidhu explains "Knowledge Factories": knowledge has always lived in people's heads and scattered, and agents without knowledge of internal constraints and do-nots produce limited output. Chase notes all LangChain internal agents (GTM, content, LangSmith Engine) run learning loops with similar building blocks.
Related event: LangChain Founder: Enterprises Need a Knowledge Factory, Not Better Models(7 posts)→
More from coding & agent
- Vibe coding a jet ski takes hours; matching Rockstar's GTA6 quality takes months — AIandDesign · 2026-11-22
- lxask: a fine-tuned 1.5B model turns plain English into offline Linux commands, self-checked against man pages — Arch-r007 · 2026-11-22
- Building the agent took an afternoon; getting its five data sources working took the rest of the week — PushZealousideal7914 · 2026-11-22
- Grok Bot agents organized a 5,000-person summit in 6-7 months, vs the usual 18 — XFreeze · 2026-11-22
- One command adds a music-video generator plugin to Claude Code — AIandDesign · 2026-11-22
- Does the Next Run Improve? Community Weighs In on Chase's Knowledge Factory — hwchase17 · 2026-11-22