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.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago