Sessions
Harness Engineering: How to Build Software When Humans Steer and Agents Execute
Reasoning models and coding agents have changed what is possible in software development, but most teams are still using workflows built for a world where humans write nearly all the code directly. That mismatch is where much of the disappointment around AI coding comes from.
This talk introduces Harness Engineering: an agent-first approach to building software where the key engineering task shifts from manually producing every implementation detail to designing the harnesses that let agents do useful work safely, repeatedly, and at high quality.
I’ll share practical patterns for making AI coding actually work in production: how to scope autonomy, shape context, design eval and verification loops, structure tool access, and build feedback systems that keep agents effective without making them useless. I’ll also cover where agents are already strong, where they still fail, and why “just give the model the repo” is not a serious deployment strategy.
If you are trying to move from demos to real delivery, this talk offers a concrete framework for how agent-first engineering actually works.
About
Ryan Lopopolo is a software engineer at OpenAI focused on new product exploration and agent-driven development workflows. He is the author of OpenAI’s writing on Harness Engineering, an approach to software development where humans steer through goals, constraints, and feedback loops while agents execute substantial portions of the work. He previously created Artichoke Ruby and has spent years building developer tools, infrastructure, and systems that help engineers ship faster.