Working Surfacelink · 22 Sep · 01
01
A small robot at the end of a fast conveyor hands each finished parcel back to the figure who ordered it, seen from behind with the back of the head showing, who opens it at the belt, while an inspector's empty desk stands beside a run-out hourglass and a stack of waiting parcels, the whole scene drawn with wide empty margins on every side.
Lenny's Newsletter

How I AI: Meta's Muse review + How Warp ships 2,000 PRs a month with AI factories

Lenny Rachitsky · 21 September 2026

Company story · critique & review · roles · Human approval

Read the original
Takeaway

Warp, which makes tools for software teams, lets the person who asked its AI agent for a code change review that change, instead of waiting for a separate reviewer.

Summary

Warp, a company that makes tools for software teams, runs an internal system called Wilson that turns a request in Slack into a tested code change. Wilson takes an average of 35 minutes to open a pull request, a proposed change to the code, but the first human review arrives 3.5 hours later. In a podcast interview recapped by Lenny Rachitsky, Warp's chief executive, Zach Lloyd, explained how the company is shortening that wait.

Key points
  • Warp lets the person who asked the agent for a change review its work, instead of requiring a separate reviewer.
  • Warp measures the system by the number of times people have to step in on each pull request, such as follow-up prompts, clarifications and corrections in review. Lloyd argues that the more steering an agent needs, the less the system really produces.
  • Lloyd expects that trust built up over time will let selected changes merge with no human review. Warp has not removed human review yet.
  • The recap adds that the system speeds up building but does not decide what to build, which still depends on user interviews, design sessions and product judgment.
Implication

Letting requesters review their own agent-built changes removes a wait but loses a second reviewer, who might notice what the requester did not ask for. This is an inference and is not Lloyd's claim, and Warp sells this kind of system.

Suggested actions
Engineering

Let the person who asked an AI agent for a code change review that change, and track how often people have to correct or redirect the agent.

Derived by Working Surface from the article. Source line: Warp has already removed one source of delay by allowing the person who prompted the agent to review its work instead of requiring a separate reviewer.

Source issue

22 September 2026: when agents write code faster than people can check it, teams move the checking into written rules and narrower reviews.