this is great for doing like toil sort of workloads, but to build more advanced like end-to-end features, we really … to be able to validate the feature first … validate sooner before we push to CI, that would be a big benefit.

Adam HudaSenior Engineering Leader, AI Developer Tools, Uber · Leader, Uber

Context. Huda is demonstrating Minion, Uber's cloud coding agent, which stops at a draft pull request.

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory, AI Engineer (YouTube), August 21, 2026, at 13:48.

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025

Filed under

Who is speaking

Adam Huda, Sr Engineering Leader for AI Dev Tools (conference affiliation, 2026). Leader of the tooling Huda presents; first-hand but promotional for the employer, and the ai.engineer bio is a conference-site profile not self-written as far as the page shows.

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, 2026-11-03).

Whisper at about 13:48-14:10 reads 'this is great for doing like toil sort of workloads, but to build more advanced like end-to-end features, we really need to be able to validate the feature first… So we can validate sooner before we push to CI, that would be a big benefit.' The passage's '…' marks the omitted words. Speaker is Adam Huda.

How to cite this passage

Adam Huda (Uber), “Agentic SDLC at Uber: Building Blocks for Uber's Software Factory”, AI Engineer (YouTube), 2026-08-21, at 13:48. https://www.youtube.com/watch?v=17-YSUHo6Lk Archived at https://the-ai-record.com/passages/uber-minion-draft-pr-validate-feature-before-ci-2026

More from the same source

And we have 2,500 skills and … more than 20,000 skill executions per day across our fleet.

Uday Kiran MedisettyDistinguished Engineer, Uber · Practitioner, Uber

Context. Medisetty is summarizing how much the managed skills are used.

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory, AI Engineer (YouTube), August 21, 2026, at 08:27.

  • 20,000 executions per day skill executions per day, at the time of the talk, 2026
  • 2,500 skills skills in marketplace, at the time of the talk, 2026

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

Today, we have 800 plus projects internally going through this, cumulatively handling more than 100 million model requests per day. This includes both the frontier models and also open source models.

Uday Kiran MedisettyDistinguished Engineer, Uber · Practitioner, Uber

Context. Medisetty is describing Uber's model gateway, the single endpoint all internal model use goes through.

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory, AI Engineer (YouTube), August 21, 2026, at 03:30.

  • 100 million requests per day model requests per day, at the time of the talk, 2026
  • 800 projects gateway projects, at the time of the talk, 2026

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

One of the other things that we're really thinking about now is bottlenecks. We're now putting more strain on our infrastructure so we're trying to anticipate where our CI capacity needs to be and make the right foundational investments there. There's only so many experiments that we can feasibly run as well. So that's another bottleneck. And then lastly, too, … decision-making … It's not about … can we build? We know we can probably build it now. It's more of a question of should we build it?

Adam HudaSenior Engineering Leader, AI Developer Tools, Uber · Leader, Uber

Context. Huda closes the talk by naming the bottlenecks that remain once agents can write the code.

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory, AI Engineer (YouTube), August 21, 2026, at 17:29.

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

So we have one context graph, we took all of the information of how Uber runs into one context graph, this has 150 unique node and edge types, we have 40 million entries there right now, it captures all the way from how our mobile apps are built, to our backend, to our … all the design docs, Jira, incident bugs, everything is connected.

Uday Kiran MedisettyDistinguished Engineer, Uber · Practitioner, Uber

Context. Medisetty is describing the single store of company context that Uber's agents read.

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory, AI Engineer (YouTube), August 21, 2026, at 09:15.

  • 40 million entries context graph entries, at the time of the talk, 2026
  • 150 node and edge types context graph node edge types, at the time of the talk, 2026

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

So we have a … assistant called Cortana, all of the things that I mentioned so far, whether it's skills, MCPs and context graph, they're all plugged into that in every surface possible, whether it's on Slack, CLI, web. So anyone in the company, they can ask a simple question, it can look up the context graph, invoke any skill, check any code, check any code in any code base, and give an answer across any of these surfaces. … in the last one month, 300 unique … created and more than 20,000 sessions per day.

Uday Kiran MedisettyDistinguished Engineer, Uber · Practitioner, Uber

Context. Medisetty is describing the assistant that packages Uber's skills, tool connections and context graph for every employee.

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory, AI Engineer (YouTube), August 21, 2026, at 10:19.

  • 20,000 sessions per day assistant sessions per day, at the time of the talk, 2026

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

if this is an autonomous diff coming from Minion, we want to give a human reviewer some confidence that this diff has gone through a lot of self-improvement already

Uday Kiran MedisettyDistinguished Engineer · Practitioner, Uber

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory (talk, AI Engineer World's Fair 2026), AI Engineer (conference organizer) YouTube channel, August 21, 2026.

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

So the key thing here is that this is actually a managed loop that you go to … We don't want thousands of loops being set up across the company without any bounds. You have a managed surface that you go to to set up the loop so it runs on Sunday when we know we have better CI capacity available.

Adam HudaSenior Engineering Leader, AI Developer Tools, Uber · Leader, Uber

Context. Huda is describing how Uber runs recurring maintenance agents against its services.

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory, AI Engineer (YouTube), August 21, 2026, at 16:25.

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

So what we built entire lifecycle around skills, so we have core skills and domain-specific skills, all of that go into a managed skills marketplace. We have 2,500 skills there right now, and it goes through a whole bunch of … automated reviews, which ensures a baseline skill quality for any skills that we have.

Uday Kiran MedisettyDistinguished Engineer, Uber · Practitioner, Uber

Context. Medisetty is describing how Uber manages the agent skills its engineers build.

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory, AI Engineer (YouTube), August 21, 2026, at 07:35.

  • 2,500 skills skills in marketplace, at the time of the talk, 2026

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

Over the last year, all of the investments we made in agentic AI have led to more than seventy percent of our PRs now either by local or cloud agents.

Uday Kiran MedisettyDistinguished Engineer · Practitioner, Uber

Talk: Agentic SDLC at Uber: Building Blocks for Uber's Software Factory (talk, AI Engineer World's Fair 2026), AI Engineer (conference organizer) YouTube channel, August 21, 2026.

  • 70% agent pr share, as of the talk (published 2026-08-21). Level not stated

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

Something wrong? Report a correction. JSON: /api/v1/passages/uber-minion-draft-pr-validate-feature-before-ci-2026.json