Review economics
vercel/ai
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 1.1× the reviews submitted of the rest.
≥10%
Attributed
a floor
12
Attributed PRs
88
Other PRs
100
Read
Attributed — the latest 5
#18377 docs: list the 24 missing packages in the root CHANGELOG index
1 reviews · 16h to merge
#18392 Backport: fix(provider/baseten): opt-in native performance client, streamed usage, error envelopes
0 reviews · 0h to merge
#18387 Backport: fix(provider/baseten): opt-in native performance client, streamed usage, error envelopes
3 reviews · 1h to merge
#17922 feat(provider/cartesia): support additional streaming PCM encodings
2 reviews · 10.0d to merge
#18367 docs(contributing): correct example path in add-new-provider guide
1 reviews · 0h to merge
The rest — the latest 5
#18410 Backport: chore(provider/gateway): update gateway model settings files v5
1 reviews · 5h to merge
#18419 [v5.0] fix: expose gateway embedding and image model ID types
1 reviews · 2h to merge
#18447 [v5.0] fix: prevent aborted tool history from blocking follow-up messages
1 reviews · 2h to merge
#18474 chore(provider/gateway): update gateway model settings files
1 reviews · 0h to merge
#18472 Backport: chore(provider/gateway): update gateway model settings files v6
1 reviews · 0h to merge
How this was measured
10% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work; 1 PR came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 9638 merged PRs — the rest have not been analyzed yet.
Detected: OpenAI Codex, Claude Code, Cursor agent.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read vercel/ai weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on vercel/ai — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository