[{"data":1,"prerenderedAt":111},["ShallowReactive",2],{"project-\u002Fprojects\u002Fagentic-devrel-pipeline":3,"projects-featured-nav":97},{"id":4,"title":5,"body":6,"category":79,"description":80,"extension":81,"featured":82,"image":83,"links":84,"meta":85,"navigation":82,"order":74,"path":86,"role":87,"seo":88,"stack":89,"stem":94,"year":95,"__hash__":96},"projects\u002Fprojects\u002Fagentic-devrel-pipeline.md","Agentic DevRel Content Pipeline",{"type":7,"value":8,"toc":72},"minimark",[9,14,18,26,30,52,56],[10,11,13],"h2",{"id":12},"overview","Overview",[15,16,17],"p",{},"Developer relations runs on technical content: tutorials, guides, example apps, and enablement material that stays in sync with a fast-moving product. At Harper, producing that content by hand was the bottleneck.",[15,19,20,21,25],{},"As Head of Developer Relations, I architected and deployed an ",[22,23,24],"strong",{},"autonomous five-agent LLM pipeline"," that streamlines how technical content is generated, so the team could spend its time on review, community, and strategy instead of first drafts.",[10,27,29],{"id":28},"approach","Approach",[31,32,33,40,46],"ul",{},[34,35,36,39],"li",{},[22,37,38],{},"Specialized agents, not one big prompt."," The work is split across five cooperating agents, each responsible for a distinct stage of producing a piece of content.",[34,41,42,45],{},[22,43,44],{},"Built around review."," The pipeline produces work for humans to approve, keeping technical accuracy and Harper's voice under editorial control.",[34,47,48,51],{},[22,49,50],{},"Grounded in the product."," Output is tied to real Harper APIs and example code, the same material behind Harper's tutorials and templates.",[10,53,55],{"id":54},"outcome","Outcome",[31,57,58,64],{},[34,59,60,63],{},[22,61,62],{},"60%+ reduction"," in content delivery time and turnaround.",[34,65,66,67,71],{},"More capacity for the rest of the role: developer education, community strategy, technical onboarding demos for enterprise partners, and hosting the Harper ",[68,69,70],"em",{},"SELECT *"," podcast.",{"title":73,"searchDepth":74,"depth":74,"links":75},"",2,[76,77,78],{"id":12,"depth":74,"text":13},{"id":28,"depth":74,"text":29},{"id":54,"depth":74,"text":55},"Production","An autonomous five-agent LLM pipeline that generates Harper's developer relations technical content, cutting delivery time by more than 60%.","md",true,null,{},{},"\u002Fprojects\u002Fagentic-devrel-pipeline","Head of Developer Relations",{"title":5,"description":80},[90,91,92,93],"LLM orchestration","AI agents","TypeScript","DevRel","projects\u002Fagentic-devrel-pipeline","2025 – 2026","bWhFq-xbEt6WOjHMAAUfSXSjV3gVM_u0vLfwaFkU3e0",[98,102,103,107],{"title":99,"path":100,"order":101},"Harper Studio","\u002Fprojects\u002Fharper-studio",1,{"title":5,"path":86,"order":74},{"title":104,"path":105,"order":106},"MetaMask Documentation","\u002Fprojects\u002Fmetamask-docs",3,{"title":108,"path":109,"order":110},"Evry Health","\u002Fprojects\u002Fevry-health",4,1792003718192]