Ryan Lopopolo: OpenAI's Framework for Shipping Code at 70 PRs/Week

**Ryan Lopopolo** (0:00)
We wanted Codex to be able to connect to our Electron app, Chrome DevTools protocol, MCP was how we started out. Eventually, I took a peek at the code, and it was entirely different. Still, Codex was connecting to the Electron app over Chrome DevTools protocol, but it was actually a local TypeScript daemon that was being spun up that was providing a little CLI interface instead of the MCP because we found that there were only two or three tool calls that we actually needed. It's more context efficient, it's faster.
And this had happened underneath me without me knowing. My workflow was not interrupted. That same dependency edge and entity relationship existed. But I almost didn't have to know how it was implemented.

**Simon Maple** (0:42)
Did you find that cool or worrying?

**Ryan Lopopolo** (0:43)
I found it. Shocking.

**Simon Maple** (0:47)
The AI Native Dev is a podcast for developers and engineering leads at the cutting edge of AI and agentic coding. Join your hosts, Guy Podjarny and me, Simon Maple, every week as we chat with the most exciting voices in AI and tackle the biggest questions facing developers today.
This is the AI Native Dev.
Hey, everyone. Hope you're enjoying the episode so far. Our team is working really hard behind the scenes to bring you the best guests, so we can have the most informative conversations about agentic development. Whether that's talking about the latest tools, the most efficient workflows or defining best practices. But for whatever reason, many of you have yet to subscribe to the channel. If you're enjoying the podcast and want us to continue to bring you the very best content, please do us a favor and hit that subscribe button. It really does make a difference and lets us continue to improve the quality of our guests and build an even better product for you. All right, back to the episode. Hello and welcome to another episode of The AI Native Dev, and we're here live at AI Native DevCon 2026 in London. And joining me is Ryan Lopopolo, who is a member of technical staff at OpenAI. So, hey folks. Ryan, how are you?

**Ryan Lopopolo** (2:04)
Doing great, excited to be here. The comp is popping, it's really fun.
I go on stage later today, and I'm just excited to get after it.

**Simon Maple** (2:12)
Absolutely, looking forward. And tell us a little bit about the session that you're giving later.

**Ryan Lopopolo** (2:15)
Yeah, so I'm gonna be talking about all things Harness Engineering, which is sort of, I guess, kind of like some of the discourse that I helped define earlier in the year here, where talk about what it means to kind of set up agents to do highly complex, autonomous, software engineering-like work in your code bases with high confidence and almost headless nature if you can get to it.

**Simon Maple** (2:36)
Yeah.

**Ryan Lopopolo** (2:37)
Lot of fancy context management techniques in order to get these agents to learn from their own mistakes, produce high quality code, and go for a very long time without human intervention.

**Simon Maple** (2:47)
Absolutely, and we're gonna talk about Harness Engineering, we're gonna talk about some of the methodologies that you've used internally at OpenAI and talk through maybe some of the bits that have been enjoyable, some of the bits that have been scary, and it's gonna be great fun. So Ryan, why don't we kick off with Harness Engineering?
For the layman, what is Harness Engineering?

**Ryan Lopopolo** (3:06)
Yeah. So we have these wonderful technology and these coding agents, and these fantastic models that are very smart and able to produce a ton of code.
And Harness Engineering is this idea that to produce code that is acceptable, to produce code that we trust, that we can build confidence in business systems around, there are a bunch of little decisions that go into the process of producing PRs, producing systems, that we have to make along the way. And in order to get the agent to know and understand those, we have to write it down. We have to make sure that the content of those choices, those non-functional requirements that go into making good code, get surfaced to the agent at the right time. So it's a combination of getting context into the repository in a place where these coding agents can see it, surfacing it to the agent at the right time, and making sure that all the code that we produce kind of like follows the golden thread of what it means for us to produce high quality software. Reviewer agents, tests, lints, big refactoring loops, all sort of ways to get the agent to close the loop and make sure that it proves to me and the rest of the team that the code it has produced is acceptable and can be merged.