[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-metas-radar-cuts-codereview-backlog-with-riskaware-automation":10},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":22,"tags":37,"sources":41,"feedback":45,"feedback_at":22,"cost_usd":45,"total_tokens":45},1406,"metas-radar-cuts-codereview-backlog-with-riskaware-automation","Meta’s RADAR cuts code‑review backlog with risk‑aware automation","A multi‑stage AI system at Meta trimmed review time and defects for over half a million code changes while keeping incidents low.","- Meta rolled out RADAR, an automated review pipeline that scores code changes for risk before deciding whether a machine or a human should approve them.\n\n- The system first flags the author and source, runs static heuristics, then applies a learned Diff Risk Score. Low‑risk diffs get an LLM‑generated review and deterministic checks; higher‑risk ones fall back to humans. In five months RADAR examined 535 K diffs and landed 331 K. Raising the risk‑score cutoff from the 25th to the 50th percentile lifted the automatic approve rate to 60.31%.\n\n- Automated reviews reverted at one‑third the rate of manual ones, and production incidents were 1\u002F50 as common. Median time to close a diff dropped by more than 330%, and wall‑time spent waiting for review fell 35%. The gains arrive as Meta’s AI‑generated code output grew 105.9% year‑over‑year, outpacing reviewer capacity.\n\n- The takeaway: layered, risk‑aware automation can keep pace with AI‑driven code growth without sacrificing safety. It shows a viable path for other large developers facing similar bottlenecks, though the benefits hinge on accurate risk scoring and the willingness to trust machines with low‑risk changes.","[\"code-review\",\"ai-tools\",\"software-engineering\"]","2026-06-16T04:00:00.000Z","2026-06-17T08:03:01.997Z","2026-06-17T08:03:04.801Z","published",null,[24,30,33],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Add a clear concluding paragraph that summarises the key impact and what readers should take away.","resolved",{"id":31,"reviewer":26,"round":32,"reason":28,"status":29},"editor-r2",2,{"id":34,"reviewer":26,"round":35,"reason":36,"status":29},"editor-r3",3,"Add a clear concluding paragraph that summarises the key impact and the takeaway for readers.",[38,39,40],"code-review","ai-tools","software-engineering",[42],{"name":43,"url":44},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.30208",0]