Speaker
Abstract
This talk explores why traditional code review is struggling to keep up with AI-driven development. It introduces a five-layer trust model designed to help engineering teams validate AI-generated code, reduce reliance on manual review, and ship faster without sacrificing quality or control.
Register
$3,250, Conference (3 days). Current pricing ends November 20th. All pass options.
76%
senior dev or higher
1:11
speaker ratio
60+
practitioners
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 the Developer Experience Hosted by Ankit Jain Co-Founder & CEO @AviatorFrom the same track
Wednesday 18 November
10:35 Ballroom A Session Features With Futures Kent Beck Original Signer of the Agile Manifesto, Author of the Extreme Programming Book Series, Rediscoverer of Test-Driven Development The value of software is the sum of: 11:45 Ballroom A Session Software Engineering No More Small Systems, How AI May Bring Large System Problems to Everyone Adam Bender Technical Lead for Enterprise Engineering @Google Once you figure out how to use AI to make your organization productive, you will soon find you have a whole new set of problems. While some of those problems will be novel thanks to LLMs, many of them are just the result of there being "more stuff". 13:35 Ballroom A Session Growing Engineers in the Era of Agentic Coding Adam Berry Staff Engineer @Netflix Early-career engineers are learning the craft in an environment where the surface they touch is often an agent, not a codebase. The instinct is to treat this as a rupture in how engineers grow. It isn't. 14:45 Ballroom A Session Software Understanding Shipping Faster, Understanding Less Margaret-Anne Storey Professor of Computer Science @University of Victoria, Co-Creator of the SPACE Framework and the Triple Debt Model for Software Health, a Canada Research Chair in Human and Social Aspects of Software Engineering AI is changing software development faster than our engineering practices are evolving, and yet many teams are facing growing pressure to ship features faster. But moving faster can create three related threats to software health: technical debt, cognitive debt, and intent debt. 15:55 Ballroom A Session How To Kill the Code Review Ankit Jain Co-Founder & CEO @Aviator This talk explores why traditional code review is struggling to keep up with AI-driven development. It introduces a five-layer trust model designed to help engineering teams validate AI-generated code, reduce reliance on manual review, and ship faster without sacrificing quality or control.