Ai Engineering Benchmarks
Ai delivery benchmarks are based on 612 merged pull requests in the last 30 days (2,727 all-time), with 1.3 hours median cycle time, 0.8 hours median review time, and 31 active contributors. AI-related signals appear on 8.7% of recent work. PR volume is up 36% 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.
AI Signals vs Cycle Time
Correlation
Cycle Time by AI-Related Signals
PR Breakdown
Top AI Tools
PR Type Breakdown
Recent Pull Requests
View PR Explorer| Title | Author | AI |
|---|---|---|
| ci: exclude pull requests from CI failure notifications | gr2m | — |
| feat(harness): support `instructions` on `HarnessAgent` to … | felixarntz | — |
| fix: preserve reasoning streams when provider deltas contai… | ai-sdk-factory | — |
| [v5.0] fix: preserve Gladia diarization and utterance detai… | ai-sdk-factory | — |
| fix(provider-utils): avoid detecting plain text prefixes as… | n1ckoates | — |
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 8 hours, 4 minutes ago.
Updated daily from public GitHub pull requests.
See Your Team's Benchmarks