Reviewing eight times the output sounds suspiciously like the old job with a new title.
Switched our team of 6 from writing PRs to reviewing them after Claude started handling roughly 70% of our agent orchestration code last quarter. Spent two weeks rebuilding our CI to run semantic diff checks and contract tests on every agent-generated branch, because eyeballing 40 PRs a day stopped scaling around week three.
Cut my Figma-to-spec handoff time roughly 70% by having Claude turn annotated frames into Storybook stubs that engineers can pull straight into PRs. The weird side effect is I spend more of my week in code review comments than in Figma now, since devs ship variants faster than I can audit them.
That "8x more code merged" stat is doing a lot of work in this post, and nobody asks whether the review bottleneck is actually being cleared or just hidden behind a queue. My students hit the same wall with AI-graded drafts: output went up, but the teacher-side check got sloppier until I capped how many AI-assisted submissions I'd accept per week. Volume isn't velocity if the reviewer is rubber-stamping.
review queue is my new standup, solo on three projects
Yeah the review bottleneck is real, that 8x stat tracks with what we see. Our two-person team ships maybe 40 PRs a week now, and I spend most Monday mornings just triaging Claude's weekend output instead of writing anything myself.
What does that 8x merge rate look like for review quality? Are reviewers catching the same defect classes they did before Claude wrote 80%?
Six months in and my actual job became reading diffs, not writing them; I'm closing maybe 12 PRs a day where I used to push 2, and most of my "work" is catching the subtle stuff Claude got 90% right but botched on edge cases. Spent last weekend learning how to write better test plans because that's the only leverage I have left as the junior.
Our team of 14 tried tracking "merged code" after rolling out Cursor and Claude Code last quarter. PR count went up 3x, sure, but our revert rate doubled and two senior reviewers burned out by month three. We had to add a second review pass for anything touching the payment service because subtle logic bugs kept slipping through. "8x more code merged" tells you nothing if you don't publish the rollback numbers next to it.
What's the merge-to-revert ratio at that 8x rate? Volume means nothing if half gets rolled back next sprint.
Same shift on my side: drafting motions takes minutes now, but vetting citations eats my afternoon. Two weeks ago I caught Claude inventing a 2019 Ninth Circuit case that sounded perfectly real, and my attorney would've signed off if I hadn't pulled the Westlaw record.
Switched from drafting discovery responses to reviewing Claude's drafts about 6 months ago, and my output went from roughly 4 sets a week to 22. The hard part now is catching the one citation in twenty that looks plausible but points to a case that doesn't say what the draft claims it says.
