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

45.5%

Merged agent PRs in significant repos.

No human reviewer

54.5%

The same significant-repo sample.

Sample

268

Significant-repo PRs behind the market rate.

Agent-Level Autonomy

Window: 2026-07-16 to 2026-08-14. 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 Copilot79.5%66.7%25 min20.8%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
Cursor70.7%40%47 min40%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
Claude Code44.4%31.7%20 min47.5%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
Amazon Q Developer41.7%35%26 min29.2%120 PRs, 120 reposexpanded 365-day window120 of 120 enrichedPublished from 365-day sample.
Devin32%13.3%22 min40.8%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
OpenAI Codex32%20%20 min62.5%120 PRs, 120 repos30-day window120 of 120 enrichedPublished
ZCode13.3%14.2%13 min55.8%120 PRs, 68 repos30-day window120 of 120 enrichedPublished
Julesn/a18.4%1.41h35.6%87 PRs, 43 repos30-day window87 of 87 enrichedLifecycle fields published. Significant-repo review rate withheld.

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.