[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-protopilot-automates-wet-lab-protocols-with-895-gate-pass-rate":10,"sections":40},{"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":30,"tags":31,"sources":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},3047,"protopilot-automates-wet-lab-protocols-with-895-gate-pass-rate","ProtoPilot Automates Wet-Lab Protocols With 89.5% Gate Pass Rate","A multi-agent AI system called ProtoPilot converts biological protocols into executable lab code, clearing an 89.5% gate pass rate across 294 benchmark tasks.","An AI system can now write, validate, and revise wet-lab protocols well enough to pass device-level execution checks nearly nine times out of ten.\n\nResearchers introduced ProtoPilot, a self-evolving multi-agent system designed to translate biological protocols into runnable lab automation code. Tested against a benchmark of 294 tasks drawn from 98 gold-standard synthetic- and molecular-biology protocols, the system achieved an overall protocol-to-code gate pass rate of 89.5% and an Opentrons-specific pass rate of 88.24%. For context, OpenTrons-AI — the existing dedicated tool — cleared just 32.35% of the same Opentrons tasks. Wet-lab runs produced Sanger-confirmed DNA products and feedback-corrected assemblies, meaning the outputs were verified in physical experiments, not just simulated.\n\nThe gap between ProtoPilot and OpenTrons-AI is wide enough to matter: more than doubling the pass rate on real instrument code suggests the multi-agent architecture — which layers protocol generation, SOP expansion, SDK-compliant code synthesis, and runtime skill updates — handles device constraints in a way that single-purpose tools do not. A 90.2% expert-preference rate on head-to-head comparisons adds a qualitative signal on top of the quantitative gate metrics.\n\nWet-lab automation has long stalled at the \"plausible but unrunnable\" stage, where AI can describe a procedure but cannot reliably translate it into instrument commands. ProtoPilot does not solve biology; it narrows the gap between a written protocol and a robot that can actually execute it — which, if it holds outside benchmark conditions, is the part that has always been the bottleneck.","[\"ai\",\"biology\",\"lab-automation\",\"multi-agent\"]","2026-07-01T04:00:00.000Z","2026-07-01T05:54:42.808Z","2026-07-01T05:54:45.680Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"The dek promises '90% protocol accuracy' but the body never mentions the overall gate pass rate of 89.5% (only the Opentrons-specific 88.24%), creating a numeric mismatch between the headline figure and the body — the 90.2% figure in the body refers to expert-preference rate, not accuracy, so the headline claim is misleading and unsupported as written; revise the headline\u002Fdek to match the specific metric being cited, or surface the 89.5% overall gate pass rate in the body to justify the '90%' fr","resolved","ai",[30,32,33,34],"biology","lab-automation","multi-agent",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.31763",0,{"sections":41},[42,46,51,56,61,66,71,76,81,86,91,95,100,105],{"name":43,"slug":30,"count":44,"latest_published_at":45},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":92,"slug":93,"count":89,"latest_published_at":94},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":106,"slug":107,"count":108,"latest_published_at":109},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]