Markdown source

The Death of the Code Review

Conference Context

Session 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.

Media Evidence

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

Evidence Graph

This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

Media Signals

Agent Reading Notes

Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

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.

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

Supporting Slides

Slide Evidence

Synthesis

Synthesized Breakdown

Hi everybody. Uh my name's Laurie Voss. I am head of developer experience at Arize AI. Uh in a former life, I co-founded npm Inc.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

Evidence Boundary

This synthesis uses the official schedule plus cached video transcripts. Official AI Engineer World's Fair San Francisco 2026 livestreams and cut videos are primary event video sources for transcript/slide evidence; external, historical, or speaker-matched videos remain supporting context unless manually verified as exact official event recordings.