“So like one, for example, one of the things we did is tagging all of our PRs to different categories, like on complexity level, and is it a feature PR bug fix maintenance testing documentation on different categories. And we could see year over year, how is that mix changing? Luckily, like at least like right now, you can see our percentage of feature PRs is going up, our percentage of maintenance PRs is going down.”
Context. Answering the host's question how Uber thinks about engineering productivity now that agents write more code. He gives no figures for the shift.
Uday Kiran Medisetty, Distinguished Engineer. Runs the engineering-productivity work Medisetty reports on and gave the AI Engineer World's Fair talk; an insider with an interest in presenting the program well.
How this was checked
Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-11-07).
Whisper transcript matches word for word. The only differences are whisper's question mark after 'different categories' and a full stop, which are punctuation only.
How to cite this passage
Uday Kiran Medisetty (Uber), “Uber's AI infra, from the inside”, The Pragmatic Engineer (YouTube), 2026-10-14, at 1:24:33. https://www.youtube.com/watch?v=MDUYSMJmi8A Archived at https://the-ai-record.com/passages/uber-feature-pr-share-up-maintenance-pr-share-down-2026
Context. Medisetty is describing Uber's background coding agent, Minion. The word cut after 'production' is pull requests (PRs), which both transcriptions rendered as 'peers'; he says 'PRs' in the next sentence.
Context. 'This' is Uber's internal model gateway, which he has just been describing (one OpenAI-compatible or Anthropic-compatible API in front of models from all vendors, with an AI Guard safety layer).
Uber