LangChain CEO's 'knowledge factory': the missing bit for enterprise AI is better knowledge, not models
hwchase17 · x · 2026-11-22
hwchase17 published "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 your company works and its standards. All LangChain internal agents (GTM, content, LangSmith Engine) run a learning loop around this idea.
Quoting jurajsalapa adds the functional angle: avoid shipping agents as copilot-studio-style connectors; instead give knowledge workers at all grades a harness with a surmountable learning curve, where each user contributes to a growing shared skills folder, with a langchain-wiki-inspired layer handling the meta.
Related event: LangChain Founder: What Enterprise AI Lacks Is a "Knowledge Factory"(14 posts)→
More from coding & agent
- Alchemy Run's distilled SDK now beats first-party AWS SDK v3 on load time — samgoodwin89 · 2026-11-22
- Open-source ComfyUI nodes for Rumble2Flash, a faster and more accurate Qwen3-ASR-based transcriber — jmbbao · 2026-11-22
- Dev praises Gemini 4 Neon but wants it available inside oh-my-pi — MilesCranmer · 2026-11-22
- Culler: open-source agent software factory with a five-role pipeline on your Mac — SufficientDrop4141 · 2026-11-22
- Dev Claims Gemini Neon Rebuilt His 5-Year SAT Solver in Under 5 Minutes, Far Faster — zakkohane · 2026-11-22
- Qwen Code ships nightly v0.28.3 with managed-agent fixes and CI hardening — qwen-code-review-bot · 2026-11-22