Speaker
Abstract
Engineering is shifting from synchronous, line-by-line implementation to an asynchronous model in which agents execute, verify, and retry while humans own intent, architecture, constraints, and release decisions.
Drawing on my experience building OpenAI Ads through Codex from day one, and scaling it to more than $100 million in ARR in under six weeks, I’ll show why the advantage does not come from a magic prompt. It comes from the system around the model: persistent workspaces, connections to real engineering tools, reusable skills, objective verification loops, and clear human boundaries around production.
Attendees will leave with a practical framework for moving faster with coding agents without surrendering engineering judgment or accountability.
Main Takeaways:
- Treat verified outcomes, not generated code, as the unit of AI-native engineering.
- Give agents measurable targets, objective feedback, and the ability to learn and retry.
$2,835, Conference (3 days). Current pricing ends September 8th. All pass options.
QCon San Francisco 2026 is a three day conference for senior software engineers, architects and team leads. An international program committee of working engineers selects every session. Patterns and practices, not products and pitches.
Part of the track
Engineering AI Systems Hosted by Melanie Zhao Engineering Lead @BlackRock, Pioneering AI Adoption in Asset ManagementFrom the same track
Tuesday 17 November
10:35 Ballroom A Session Progressive Failure Modes of Modern AI Serving Systems Abi Aryan AI Infrastructure Engineer and Educator Inference platforms fail in layers. Most organizations focus on model quality while underestimating the systems engineering required to operate production AI workloads safely and reliably at scale. 11:45 Ballroom A Session The Revenge of the Data Scientist: Why Reliable AI Needs Evals, Traces, and Metrics Hamel Husain Machine Learning Engineer, 20+ Years in Applied AI, Machine Learning, and Data Science Most teams can now ship an AI prototype by calling a foundation-model API. The hard part is knowing whether that system works when real users, messy data, and business consequences arrive. 13:35 Ballroom A Session Skills, Memory, or Fine-Tuning? The Engineering Loop Behind Self-Improving Agents Abhinav Sinha CEO @Lucidic AI, Previously @Stanford AI Lab, @Citadel and Susquehanna International Group, and @Apple As agents become mainstream, everyone wants to improve theirs either by making fewer mistakes on existing tasks or by taking on harder ones. This usually happens once an agent is already deployed in production. 14:45 Ballroom A Session Lessons from Building a $100M Product in Six Weeks at OpenAI Brian Yang Member of Technical Staff @OpenAI Engineering is shifting from synchronous, line-by-line implementation to an asynchronous model in which agents execute, verify, and retry while humans own intent, architecture, constraints, and release decisions. 15:55 Ballroom A Session Performance Engineering in the Age of AI Details coming soon. 17:05 Seacliff D Unconference Unconference: Engineering AI Systems