Review economics
Canner/WrenAI
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 1.0× the reviews submitted of the rest.
≥14%
Attributed
a floor
15
Attributed PRs
85
Other PRs
100
Read
Attributed — the latest 5
#2644 feat(ui): surface a Wren AI Cloud upgrade entry point in the sidebar
0 reviews · 3h to merge
#2632 docs(core): align quickstart with the jaffle_shop tables it actually builds
1 reviews · 1h to merge
#2610 deps(sdk): raise the wrenai floor to 0.13.1
1 reviews · 13h to merge
#2603 test(snowflake): fix the mock patch target so the suite actually runs
1 reviews · 3h to merge
#2602 docs: set an explicit contribution bar for agent-authored PRs
3 reviews · 3h to merge
The rest — the latest 5
#2647 fix: target legacy release tags at workflow revision
0 reviews · 0h to merge
#2646 Release 0.29.2 (ai-env-changed)
0 reviews · 0h to merge
#2574 fix(spark): apply limit via DataFrame.limit before toPandas
1 round · 6 reviews · 11.9d to merge
#2619 fix(core): keep RLAC cycle-detection state per analyzer invocation
4 reviews · 6.7d to merge
#2624 refactor(connector): centralize LIMIT coercion
5 reviews · 5.9d to merge
How this was measured
14% 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; reads 100 of 1539 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code.
“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 Canner/WrenAI 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 Canner/WrenAI — 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