Review economics
GoogleCloudPlatform/knowledge-catalog
Read from the 41 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.0× the reviews submitted of the rest.
≥19%
Attributed
a floor
4
Attributed PRs
37
Other PRs
41
Read
Attributed — the latest 4
#227 okf: migrate format and tooling to Open Knowledge Format v0.2
0 reviews · 17h to merge
#130 okf: refocus README title and intro on the format
0 reviews · 0h to merge
#129 okf: rename enrichment_agent package to reference_agent
0 reviews · 0h to merge
#34 Add dynamic (golden-free) enrichment evaluation CLI
0 reviews · 0h to merge
The rest — the latest 5
#269 mdcode: generate BigQuery property-graph DDL from the Semantic Model IR
29 reviews · 11h to merge
#258 mdcode: add Semantic Model IR and model loader
17 reviews · 2.5d to merge
#108 Feat/confluence sharepoint okf sources
0 reviews · 0h to merge
#103 Enrichment agent: cross-cutting hybrid KB, per-entry table fact_recall, public goldens + kcmd sync
0 reviews · 0h to merge
#42 Sync enrichment agent + evaluation harness into agents/enrichment
0 reviews · 0h to merge
How this was measured
19% 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.
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 GoogleCloudPlatform/knowledge-catalog 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 GoogleCloudPlatform/knowledge-catalog — 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