--- title: QCon AI Boston: Production AI Moves Beyond Prompts to... description: QCon AI Boston 2026 highlighted a shift in AI development focus from building agents to running them reliably in production. Key themes included context... canonical: https://daily.dev/posts/qcon-ai-boston-production-ai-moves-beyond-prompts-to-platforms-harnesses-and-evals-jonkilvji twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: QCon AI Boston: Production AI Moves Beyond Prompts to Platforms, Harnesses, and Evals | daily.dev og:description: QCon AI Boston 2026 highlighted a shift in AI development focus from building agents to running them reliably in production. Key themes included context... og:url: https://daily.dev/posts/qcon-ai-boston-production-ai-moves-beyond-prompts-to-platforms-harnesses-and-evals-jonkilvji og:image: https://api.daily.dev/og/posts/jonkilVjI.png og:image:alt: QCon AI Boston: Production AI Moves Beyond Prompts to Platforms, Harnesses, and Evals og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # QCon AI Boston: Production AI Moves Beyond Prompts to Platforms, Harnesses, and Evals **[InfoQ](https://daily.dev/sources/infoq)** · 4 min read · 0 upvotes · 0 comments ## Summary QCon AI Boston 2026 highlighted a shift in AI development focus from building agents to running them reliably in production. Key themes included context engineering as core infrastructure (not just a feature), security through agent 'harnesses' that enforce state ownership, approval boundaries, and audit trails, and AI adoption becoming a full engineering operating model requiring observability, cost attribution, and evaluation loops. A major insight was that single-turn tests and static benchmarks are insufficient for stateful, multi-turn agents — evaluation must mirror real product behavior through conversations, traces, and production feedback. The conference signaled that production AI is now a systems engineering problem, with the infrastructure around the model mattering as much as the model itself. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [QCon AI Boston’s Early Program Focuses on the Engineering Work Behind Production AI](https://daily.dev/posts/qcon-ai-boston-s-early-program-focuses-on-the-engineering-work-behind-production-ai-f0tijvrok) · InfoQ · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#context-engineering](https://daily.dev/tags/context-engineering) [View this post on daily.dev](https://daily.dev/posts/qcon-ai-boston-production-ai-moves-beyond-prompts-to-platforms-harnesses-and-evals-jonkilvji) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"QCon AI Boston: Production AI Moves Beyond Prompts to Platforms, Harnesses, and Evals","url":"https://daily.dev/posts/qcon-ai-boston-production-ai-moves-beyond-prompts-to-platforms-harnesses-and-evals-jonkilvji","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/qcon-ai-boston-production-ai-moves-beyond-prompts-to-platforms-harnesses-and-evals-jonkilvji"},"datePublished":"2026-07-17T09:01:23.718Z","dateModified":"2026-07-18T07:27:50.990Z","description":"QCon AI Boston 2026 highlighted a shift in AI development focus from building agents to running them reliably in production. Key themes included context...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4dd6dba845faa1b901f3d04d974a82af?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4dd6dba845faa1b901f3d04d974a82af?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"InfoQ","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"InfoQ","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/afc3bced3e1e4b188dd9127017a60e0c","url":"https://daily.dev/sources/infoq"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/qcon-ai-boston-production-ai-moves-beyond-prompts-to-platforms-harnesses-and-evals-jonkilvji","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,mcp,context-engineering","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"InfoQ","item":"https://daily.dev/sources/infoq"},{"@type":"ListItem","position":3,"name":"QCon AI Boston: Production AI Moves Beyond Prompts to Platforms, Harnesses, and Evals"}]} ```