Building uReview, Uber’s Multi-Agent Code Review Engine — Will Bond & Ameya Ketkar, Uber
Uber built a system called uReview in 2024 that uses AI agents for code review, after wait times for human reviews grew from three to nine hours.
The system posted approximately 25,000 comments per week and resolved 67 percent of the issues it identified, while costs decreased 60 percent compared to the first version. Uber's challenge was not creating the AI agents but running them at scale cheaply and measuring the right metrics—including comment sentiment, whether issues were actually addressed, and agent performance over time—in order to adjust the system.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More to read
Lumaril, which develops AI software for optimizing industrial production by connecting to existing control systems, raised a $66M Series A at a $400M valuation
Techmeme 3 h ago
DeepSeek open sources Super-Agent as a research prototype, a proactive coding agent it says can monitor group chats for coding issues and suggest solutions
Techmeme 3 h ago
Insurance software maker Guidewire agrees to acquire Hyperexponential, which makes AI-powered insurance underwriting and pricing software, for $1.7B in cash
Techmeme 3 h ago
One word for AI agents in 2027
Nate Herk 7 h ago