LangChain's Harrison Chase: Companies Need a 'Knowledge Factory,' Not Better Models
hwchase17 · x · 2026-11-22
LangChain founder hwchase17 published a long post, "How to build a knowledge factory," arguing that the missing piece for enterprise AI is neither better models nor simply more context, but better knowledge: how the company works, its operating standards, where data lives and how it is accessed.
- Top employees carry this knowledge in their heads — who to ask, where to look, why things are done a certain way. It is tacit, implicit and scattered, sometimes only in someone's head, sometimes across documents.
- To make AI work, companies must collect, curate and maintain a representation of that knowledge to pass to agents; the system that does this is what LangChain calls a knowledge factory.
- LangChain has built this internally in several ways, including for GTM (post truncated at that point).
Related event: LangChain Founder: Enterprises Need a Knowledge Factory, Not Better Models(2 posts)→
More from coding & agent
- Dev ditches SaaS for self-built AI tools; investor sees selective buying opportunity — craigbalding · 2026-11-22
- Charting the Singularity: a Claude-powered world model run on 60K+ prompts — MauiHawk · 2026-11-22
- Beyond AI Coding: Developers Should Move to the Five-Layer Agentic Engineering Stack — Pavan_Belagatti · 2026-11-22
- PSAISuite Pipes Native PowerShell Cmdlets Into Multi-Model Agent Harness — dfinke · 2026-11-22
- Testing shows renaming a Git checkout doesn't change MemoraX's memory scope ID — Elegant-Chance-6420 · 2026-11-22
- Lean 4 formalization of Masullo's Riemann proof hits 51%: 1213 of 2385 theorems proved — bremen79 · 2026-11-22