LangChain CEO's 'knowledge factory': what enterprise AI lacks is curated knowledge, not models
hwchase17 · x · 2026-11-22
LangChain founder Harrison Chase published "How to build a knowledge factory", arguing the missing piece for enterprise AI is not better models or more context, but better knowledge — the tacit know-how of how the company operates, its standards, and where data lives.
He reveals all internal LangChain agents (GTM, content, LangSmith Engine) run learning loops on this principle: context 2.0 is about self-evolution, continuous curation, and proactively injecting the right know-how at the right time.
Related event: LangChain Founder: What Enterprise AI Lacks Is a "Knowledge Factory"(10 posts)→
More from coding & agent
- 'Knowledge factory': turning agent corrections into reusable knowledge before everyone reteaches it — hwchase17 · 2026-11-22
- Antigravity agent opens browser, drives Gemini's website to run Deep Research on its own — MParakhin · 2026-11-22
- Build a "deal desk" agent trained on your past proposals to guard every pricing decision — VibeMarketer_ · 2026-11-22
- Agent swarm locks out cofounder for 24+ hours: Simeon Campos on multi-agent dynamics — repligate · 2026-11-22
- Dev builds Omi, an Android agent that operates any app like a human, no API needed — cyka_6lyat · 2026-11-22
- Dev builds sandboxed browser plugin for Claude Code that clicks through pages and evades bot detectors — jradoff · 2026-11-22