{
  "id": 7908937,
  "title": "Reduce PR review time with AI: the bottleneck is the wait, not the read",
  "url": "https://urgent.news/2026/09/17/reduce-pr-review-time-with-ai-the-bottleneck-is-the-wait-not-the-read",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-17T00:15:11.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/cole_halton_42f71d71b809b/reduce-pr-review-time-with-ai-the-bottleneck-is-the-wait-not-the-read-2nab"
  },
  "original_language": "en",
  "account": "A recent study shows that AI-generated pull requests face a significant delay before they are reviewed, rather than the review process itself. On average, an AI PR waits 16 hours before a human opens it, while manual PRs are reviewed within 200 minutes. This delay is the real bottleneck, not the review time. The AI PRs also have a lower merge rate, with only 32.7% merging within 30 days, compared to 84.4% for manual PRs. Reviewers are hesitant to approve AI PRs with more than 408 lines of code, as they fear missing important context. The data suggests that AI can speed up the review process by reducing the time it takes for a reviewer to pick up the PR, but the overall merge rate remains low. Therefore, the focus should be on improving the \"waiting\" part of the review process rather than just the review itself.",
  "summary": "Linearb's 2026 Engineering Benchmarks Report analyzed 8.1+ million pull requests across 4,800+ organizations, and one finding cuts against most of what you read about AI review speed. AI-generated PRs wait 4.6x longer before anyone picks them up. But once they're picked up, they get reviewed 2x faster than manual work. So the time you're trying to shave with AI isn't the reading part. It's the…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}