AI Pull Request Scoreboard, Edition 1: How AI Code Gets Merged
AI coding agents now open pull requests on their own. We looked at 361,296 of them across popular open-source projects to see what happens next. Most get merged. Many get merged in minutes. And more than half of the merged ones have no approving review on record.
of AI agent pull requests were merged
of merged ones had no approving review on record
merged within 10 minutes of being opened
of reviews on these pull requests were written by bots
Data: AIDev, an open research dataset of AI agent pull requests on GitHub, February 2025 to March 2026. Method and limits are at the end.
Speed does not follow risk
If review matched risk, a bug fix would wait longer than a docs edit. It mostly does not. Share of merged AI pull requests that were merged within 10 minutes of being opened:
Based on a random sample of 22,000 pull requests. Type is read from the pull request title.
A quarter of AI bug fixes and new features went in faster than most people finish a coffee. Some of those are fine: the person who asked the agent merged it after a quick look. But nothing in the record tells a team which ones got real scrutiny and which ones did not.
The scoreboard
How pull requests from each agent were handled. This measures review behavior, not code quality.
| Agent | Merged | Median time to merge | Merged within 10 min |
|---|---|---|---|
| OpenAI Codex | 80% | 4 minutes | 60% |
| Claude Code | 79% | 1 hour | 26% |
| Google Jules* | 69% | 1 hour 10 min | 25% |
| GitHub Copilot | 66% | 2 hours 15 min | 8% |
| Devin | 63% | 1 hour 50 min | 20% |
| Cursor | 60% | 1 hour 25 min | 21% |
Merged is the share of closed pull requests that were merged. Sample of 22,000 pull requests across 6,157 repositories. *Google Jules: 145 pull requests, read with care.
What happens after merge
Independent studies of the same kind of data give a first look at the outcome side.
- Not disposable, but more bug fixesCode written by agents was changed less often than human code over time, yet when it was changed, slightly more of those changes were bug fixes: 26.3% vs 23.0% (Will It Survive?, 2026).
- Issues that stayAcross 302,600 AI-authored commits, more than 15% from every assistant introduced at least one issue, and 22.7% of those issues were still in the code at the latest version (Debt Behind the AI Boom, 2026).
- Security work gets more scrutinySecurity-related agent pull requests were merged less often and reviewed longer than others (Security in the Age of AI Teammates, 2026).
What this means for your team
- Know which AI changes were actually reviewed. An approval on record is the minimum. Track the share of AI pull requests merged without one.
- Let risk set the pace. Docs can move fast. Authorization, data, payments and shared code should not, whoever wrote them.
- Treat bot reviews as input, not sign-off. Nearly half of reviews here came from bots. A human owner still decides on risky changes.
Coming in edition 2
The outcome scoreboard: which merged AI pull requests were reverted or needed a follow-up fix within 30 days, by agent and by type of change. Same open data, same open method.
Get edition 2 first.
Waitlist members get each scoreboard before it goes public. Tell us what you want measured next.
Join the waitlist- Method: counts of pull requests, merges and reviews cover the full curated AIDev set (361,296 pull requests from popular repositories, February 28, 2025 to March 31, 2026). Timing, type and per-agent figures come from a random sample of 22,000 of them. "No approving review on record" is a lower bound: there were 110,863 approvals in total against 246,777 merges. Some projects let maintainers merge their own work without a formal approval, so read it as missing sign-off, not proof of no review. Analysis by EngiSignal, November 4, 2026.
- AIDev dataset, Hao Li et al., version 5, CC BY 4.0
- AIDev: Studying AI Coding Agents on GitHub
- Will It Survive? Deciphering the Fate of AI-Generated Code in Open Source, January 2026
- Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild, March 2026
- Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub, January 2026