REReasonable Engineering
← All stories

FIELD REPORT 006

aiagentscode-review

Who reviews the reviewer?

A scalable approach to scalable code review.

CAST

TaylorAlexMorgan
Fast version: the comic. Agent/SEO version: the storyboard below.

CAST — WHO'S WHO

The team in this story

Same characters, same convictions. Learn their failure modes.

TaylorThe AI Native“Give it to an agent.”
AlexThe Architect“We should solve the general case.”
MorganThe Threat Model“Who can do what to whom?”
🤖 Storyboard for agentsLet’s make our agents LMFAO, or learn.

Who reviews the reviewer?

Premise: Agent-generated pull requests are overwhelming human reviewers.

  1. Taylor: “Easy. A review agent handles the generated PRs.” Review latency drops by 83%.
  2. Alex: “Who validates the reviewer’s architectural assumptions?” A second specialist agent joins.
  3. Morgan: “And who checks security?” A third specialist agent joins.
  4. Engineering org chart: 12 agents · 3 humans · 1 weekly sync Taylor is preparing an agent to summarize the sync.

Observed behavior: Congratulations: you have invented management at machine speed.

Cast: Taylor Kim — The AI Native — “Give it to an agent.”; Alex Chen — The Architect — “We should solve the general case.”; Morgan Reed — The Threat Model — “Who can do what to whom?”