How-to

Harrison Chase:构建智能体的关键是打造知识工厂

Why we picked it

LangChain 创始人 Harrison Chase 发的一条短推,观点很直接:做智能体的瓶颈不在写代码,而在上下文。他把这上升到组织层面,说该建的是知识工厂。做 agents 的人花一分钟看完,会对自己的工程优先级有新的排序。

LangChain 创始人 Harrison Chase 在 X 上发文提出,SaaS 依赖软件运行,所以每家公司都在建设软件工厂,而智能体开发中最难的部分是上下文(context),即智能体所掌握的知识。

Body

他认为,如果你在做智能体(agents),真正应该建设的不是软件工厂,而是一座知识工厂——持续生产、组织和维护供智能体消费的知识。

这条观点延续了 LangChain 近期在 context engineering 方向的主张,把上下文工程从工程技巧上升为一种组织级的系统性建设,对正在搭建智能体产品的开发者有直接的思路参考。

Original · Harrison Chase

saas runs on software, so everyone is building a software factory the hardest part of building agents is the context (or knowledge that they have) if youre building agents, you should be building a knowledge factory📊 10 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include LangChain, Harrison Chase, agents, context engineering.

Source attribution: curated from Harrison Chase (@hwchase17).