Skip to content
All posts

SERIES · 13 POSTS · 80 MIN

AI and Code Review

Code generation got cheap; understanding stayed expensive. This series follows that inversion end to end: what AI reviewers actually catch, how to review code an agent wrote, what bot noise does to reviewer attention, and the division of labor that keeps a human owning the merge.

Start with Reviewing AI-generated code: a practical checklist

READING ORDER

Read it in order.

  1. 01Reviewing AI-generated code: a practical checklistHow to review AI-generated code: a practical checklist covering intent match, hallucinated APIs, untested edges, security surface, and testing the tests.8 min
  2. 02AI writes code faster than you can review itAuthoring got 50% faster; reviewing didn't. Why the AI code review bottleneck is structural, what it does to teams, and the three places to attack it.6 min
  3. 03AI code review tools: what they actually catchHow accurate is AI code review? Independent testing shows most suggestions duplicate linters, some are wrong, a few are gold. How to evaluate a tool honestly.6 min
  4. 04Alert fatigue comes for code reviewAI review false positives don't just waste time; they teach your team to ignore the bot, real catches included. How to tune a reviewer for trust.5 min
  5. 05AI PRs are burning out open source maintainersAI-generated PRs arrive in minutes; review still happens at volunteer speed. The data behind open source maintainer burnout, and what projects can do.6 min
  6. 06What AI should (and shouldn’t) do in code reviewWhere AI in code review actually helps: upstream as a quiet pre-filter, humans downstream on a fast surface. Why Pyor writes no AI summary of your PR, by design.6 min
  7. 07Agentic code review: how review changes when agents write the codeAgentic code review means reviewing code whose author is a model: absent intent, tiered rigor by blast radius, and a human who still owns the merge.7 min
  8. 08AI code change intent documentation: capture the why before the session diesAI code change intent documentation keeps the reasoning after the agent session ends: what was asked, what was chosen, what was rejected, what is untested.6 min
  9. 09When AI changes tests to pass, green CI stops meaning correctWhen AI changes tests to pass, green CI stops meaning correct. Why reviewers should read test diffs first and how to protect assertions from quiet rewrites.6 min
  10. 10Prompt injection is now a code review problemPrompt injection code review: how hidden instructions in READMEs, comments, and issues steer AI agents and reviewers, and a checklist for catching them.6 min
  11. 11Multiple AI code reviewers: when parallel bots help and when they just multiply noiseMultiple AI code reviewers barely overlap in what they find. When parallel review bots are worth the noise, and when one well-tuned reviewer wins.6 min
  12. 12Junior developers, AI code review, and the learning loop we are quietly breakingHow junior developers and AI code review collide: unclear ownership when agents write full PRs, and the norms that protect the learning loop.6 min
  13. 13You should read the code, not the AI summaryAn AI code review summary is a claim about the diff, not the diff. Why reading the code stays the reviewer's job, and how to use summaries without being used.6 min

More on review,in the archive.

Free on your personal account. Teams are $7.99 per seat / month billed yearly, or $9.99 monthly, with Pyor AI included, and start with a 30-day trial, no card.