Uber 内部 19 个 AI 相关系统案例预告：企业级智能体为何必然复杂
Gergely Orosz 要拆 Uber 内部 19 个 AI 系统，看看大公司怎么应对上下文窗口不够用的难题。
工程师 Gergely Orosz 在 X 上指出，中型以上公司的 agentic AI 系统必然复杂，因为企业内部上下文太多，而模型的上下文窗口有限。他预告将在 Pragmatic Engineer 发布 Uber 案例研究，梳理其 19 个内部定制的 AI 相关系统。其中不少是 AI 兴起前就存在的旧系统，如今在 AI 场景下很有用，例如 PRD+ERD 系统记录了 Uber 约 5,000 个内部系统之间的连接关系，可供智能体检索。
I don't think most people realize how complex and complicated agentic AI systems inside mid-sized and above companies are: by necessity, because there is SO MUCH context, but only so little AI contex windows.
Case study on Uber's 19 internal, custom, AI-related systems coming later today in @Pragmatic_Eng
So many of those "AI-related systems" are "systems pre-AI" that turned out to become extremely useful with AI. Like their PRD+ERD system that conveniently documents connections between the ~5,000ish internal systems inside the company!
