Agentic SDLC at Uber — Uday Kiran Medisetty & Adam Huda, Uber
Uber has built infrastructure enabling AI agents to write code—over 70 percent of their code reviews now come from automated agents instead of humans.
The system works through six major components: a central gateway that scans every AI call for security in under 100 milliseconds, a system reducing the data agents need to keep in memory (cutting tokens by 40 percent), a database with 2,500 pre-built code tools, and a network of 40 million data collections replacing many separate systems. The entire workflow is controlled from Slack, and agent work is intentionally stopped before entering the build queue so humans can first verify screenshots against design files.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
