Four figures seen from behind, the backs of their heads showing, lean over a long table to study one unrolled blueprint, while a small robot at the end of the table waits with its tools folded beside a layered cake already cut into thin upright slices, and a tall pile of paper stands untouched in the corner, the whole scene drawn with wide empty margins on every side.

SEP

So, AI Killed Your Code Review Process. Now What?

Nicole Selig · 22 September 2026

Company story · critique & review · rituals · Work cut to size

Takeaway

An engineer at a software consultancy argues that when AI-written code outgrows review, teams should cut work into thin slices and review the agent's plan before any code exists.

Summary

Nicole Selig is an engineer at SEP, a software consultancy. She writes that code review broke down once AI agents produced changes larger and faster than people could read them. Her remedy is established practice rather than new tools.

Key points

Selig recommends cutting work into vertical slices, thin pieces that each run end to end through a feature, so that each change stays small enough to review.
The team reviews the agent's implementation plan together before any code is written.
Clean-up of existing code is done as a separate step, and feature flags and gradual releases catch problems after a change is merged.

Implication

The size of a change is set when the work is planned, so the people who plan the work also set the reviewers' load. This is an inference and is not the author's claim.

Suggested actions

Engineering

Cut each agent-built feature into thin slices that each work end to end, and review the agent's implementation plan as a group before any code is written.

Derived by Working Surface from the article. Source line: It's designing our workflows so they don't have to.

Source issue

23 September 2026: people keep up with agent-built work when it arrives small and already checked, and when they have learned to judge it.