Skip to content
View original post on X: Gergely OroszX· 26/100AI score26/100

Gergely Orosz previews Uber's 19 internal AI systems case study

AISummary

Gergely Orosz says agentic AI systems inside mid-sized and larger companies are complex because the relevant context is vast while AI context windows remain small.

He previews a case study on Uber's 19 internal AI-related systems, noting many were built before AI and became useful with it. One example is Uber's PRD+ERD system, which documents connections among its roughly 5,000 internal systems.

Post on XView on X
Gergely OroszVerified on X
@GergelyOrosz

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!

Source: Gergely Orosz · x.comPublished · added here

Topics

AI agentsDeployment & engineeringExpert opinion