YouTube21 Aug 2026
18m

Agentic SDLC at Uber — Uday Kiran Medisetty & Adam Huda, Uber

Podcast cover

AI Engineer

Uber’s managed software factory leverages agentic AI to significantly accelerate engineering productivity, resulting in over 70% of pull requests now generated by local or cloud agents. This infrastructure relies on six core building blocks: a secure model gateway for PII protection, an MCP gateway for tool integration, cloud-based DevPods for isolated environments, a managed skills marketplace, a comprehensive context graph, and a centralized AI assistant named Cortana. These components streamline the software development life cycle, shifting validation and code review tasks into the inner loop to reduce CI strain. By integrating these tools, engineers can automate complex tasks, from initial feature ideation and design prototyping to autonomous coding and maintenance. This architectural shift enables faster feature delivery and improved code quality, allowing teams to focus on strategic decision-making rather than repetitive manual toil.

Outlines

Sign in to continue reading, translating and more.

Open full episode in Podwise