Sign up to save your podcasts
Or
Share Ryan Lopopolo: OpenAI's Framework for Shipping Code at 70 PRs/Week
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Ryan Lopopolo: OpenAI's Framework for Shipping Code at 70 PRs/Week
Most engineering teams are still arguing about whether to use AI coding agents.
Ryan Lopopolo's team at OpenAI shipped an entire product with no human-written code — and onboarding a new engineer made the team faster within two weeks.
That outcome didn't come from better prompts. It came from what Ryan calls Harness Engineering: the systems, constraints, and feedback loops that sit around the agent — the context it sees, the tools it can call, the tests and linters that close the loop, and the asynchronous CI jobs that catch slop before it compounds.
We sat down with Ryan at AI Native DevCon London 2026, and he got into the specifics: how his team went from 3.5 PRs per engineer per week to 70, why he inverts spec-driven development (build the code first, distill the spec second), and what he means when he says it's "borderline negligent" not to use a billion tokens a day.
It's one of the most grounded, production-focused conversations we've had on The AI Native Dev. The trailer is live now — and the full episode drops this week.
#HarnessEngineering #AINativeDev #SoftwareEngineering
Join the AI Native Dev Community on Discord: https://tessl.co/4ghikjh
Ask us questions: [email protected]
View all episodes
By TesslMost engineering teams are still arguing about whether to use AI coding agents.
Ryan Lopopolo's team at OpenAI shipped an entire product with no human-written code — and onboarding a new engineer made the team faster within two weeks.
That outcome didn't come from better prompts. It came from what Ryan calls Harness Engineering: the systems, constraints, and feedback loops that sit around the agent — the context it sees, the tools it can call, the tests and linters that close the loop, and the asynchronous CI jobs that catch slop before it compounds.
We sat down with Ryan at AI Native DevCon London 2026, and he got into the specifics: how his team went from 3.5 PRs per engineer per week to 70, why he inverts spec-driven development (build the code first, distill the spec second), and what he means when he says it's "borderline negligent" not to use a billion tokens a day.
It's one of the most grounded, production-focused conversations we've had on The AI Native Dev. The trailer is live now — and the full episode drops this week.
#HarnessEngineering #AINativeDev #SoftwareEngineering
Join the AI Native Dev Community on Discord: https://tessl.co/4ghikjh
Ask us questions: [email protected]