Ai Engineering Benchmarks
Ai delivery benchmarks are based on 634 merged pull requests in the last 30 days (3,703 all-time), with 0.9 hours median cycle time, 0.6 hours median review time, and 37 active contributors. AI-related signals appear on 9.0% of recent work. PR volume is up 7% compared to the prior period.
Repo vs Vercel Average
Delivery Trend and AI Signals
PR Backlog (Humans)
Excludes AI agents and automation accounts.
PR Backlog (AI Agents)
AI coding agents only.
Cycle Time by AI-Related Signals
PR Breakdown
Top AI Tools
PR Type Breakdown
Recent Pull Requests
View PR Explorer| Title | Author | AI |
|---|---|---|
| docs: improve getting started guides and add Angular quicks… | gr2m | — |
| docs: backport getting started updates to v6 | gr2m | — |
| docs: backport getting started updates to v5 | gr2m | — |
| docs: add Chat SDK integration docs | bensabic | — |
| fix(harness): ensure harness adapters always resolve the mo… | felixarntz | AI |
Methodology
Metrics are computed from merged pull request data synced daily from GitHub. AI-related metrics are directional signals inferred from pull request activity patterns and heuristics. Summary metrics use a 30-day rolling window; trends use a 90-day window. Last updated 10 hours, 13 minutes ago.
Updated daily from public GitHub pull requests.
See Your Team's Benchmarks