Amplifying/agent-intelligence
/coding-agentsAutonomy sample

AutonomyPreview

Public GitHub can show whether merged agent pull requests had a human reviewer, how long they took to merge, and whether they touched tests. Significant repos are org-owned or have at least 10 stars. Agent-level rates are withheld when the sample is too concentrated. Sparse exact-bot agents can use an expanded window; those rows are not included in the market rate.

Human reviewed

50.8%

Merged agent PRs in significant repos.

No human reviewer

49.2%

The same significant-repo sample.

Sample

252

Significant-repo PRs behind the market rate.

Agent-Level Autonomy

Window: 2026-06-25 to 2026-07-24. Published rates require at least 40 capped PRs across 15 repos. Significant-repo review rates require at least 10 significant PRs across 8 significant repos.

AgentSignificant reviewAll-repo reviewTime to mergeTests touchedSampleStatus
GitHub Copilot75%68.3%38 min26.7%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
Cursor62.8%35.8%28 min45%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
OpenAI Codex56.5%36.7%35 min66.7%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
Claude Code51.4%26.7%11 min45%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
Devin42.1%15.8%14 min23.3%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
Amazon Q Developer37%36.7%27 min30%120 PRs, 120 reposexpanded 365-day window120 of 120 enrichedPublished from 365-day sample.
Jules26.1%19.2%1.4h17.5%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
ZCode23.8%25%23 min48.2%112 PRs, 63 repos30-day window112 of 112 enrichedPublished

Read This With the Ranking

Output volume counts what an agent leaves visible. Autonomy adds the lifecycle read: whether merged work had a human reviewer, how quickly it merged, and whether tests changed. For capture details and visibility limits, see the methodology.