The Death of the Code Review

Official Schedule Context

Summary

Laurie Voss frames code review as a process built around human-authored diffs and argues that AI-native software teams need a different control point: automated verification that can decide whether generated code is safe to ship. The connected supporting material, especially Voss's AI Engineer talk on hands-on evals for agentic applications, points toward evaluation harnesses as the replacement layer: systems that capture reviewer judgment, test agent behavior, and turn recurring review patterns into repeatable checks. In the World's Fair context, this session sits squarely in the Software Factories theme: moving from artisanal review toward production pipelines where coding agents, prompts, tests, evals, and observability form the release gate.

Official Description

Code review was built for a world where humans wrote all the code. Now, the question isn’t “does

this diff look good?” — it’s “can this system safely ship code on its own?” This talk will show why

and how traditional code review will quietly be replaced by automated verification harnesses. We’ll

show how prompt learning can be used to clone your best internal code reviewers, turning their

judgment into automated evaluation loops. We’ll also open source a code review training harness that

captures review patterns and turns them into reusable checks for AI-generated code.

Related YouTube Video

Ship Real Agents: Hands-On Evals for Agentic Applications — Laurie Voss, Arize (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

Transcript Status

Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Cached at raw/sources/youtube-transcripts/Xfl50508LZM.txt (22,591 words).

People

Notes

Supporting Slides

Slide Evidence