--- title: How we ship models in VS Code | LIVE161 | daily.dev description: A VS Code product manager explains the behind-the-scenes work required to ship new AI models in GitHub Copilot. Each model — even within the same family like... canonical: https://daily.dev/posts/how-we-ship-models-in-vs-code-live161-3fywc3ys9 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How we ship models in VS Code | LIVE161 | daily.dev og:description: A VS Code product manager explains the behind-the-scenes work required to ship new AI models in GitHub Copilot. Each model — even within the same family like... og:url: https://daily.dev/posts/how-we-ship-models-in-vs-code-live161-3fywc3ys9 og:image: https://api.daily.dev/og/posts/3FYWc3YS9.png og:image:alt: How we ship models in VS Code | LIVE161 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. # How we ship models in VS Code | LIVE161 **[Visual Studio Code](https://daily.dev/sources/vscode)** · 16 min read · 0 upvotes · 0 comments ## Summary A VS Code product manager explains the behind-the-scenes work required to ship new AI models in GitHub Copilot. Each model — even within the same family like GPT 4 to 5.5 — has its own 'personality' requiring a custom coding harness with tailored system prompts, tool call configurations, and context management. The team works closely with model providers (OpenAI, Anthropic) to optimize these harnesses before launch. They use both public benchmarks like SWE-bench (as regression tests) and an internal benchmark called VSC-bench with 100+ tasks to evaluate model performance via 'report cards' tracking resolution rates. Post-launch optimization continues iteratively, and offline evals are highlighted as a critical practice for anyone building their own coding harness. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Auto model selection is generally available in GitHub Copilot in Visual Studio Code](https://daily.dev/posts/auto-model-selection-is-generally-available-in-github-copilot-in-visual-studio-code-cvhnbwf95) · GitHub Changelog · 0 upvotes · 0 comments - [Introducing auto model selection \(preview\)](https://daily.dev/posts/introducing-auto-model-selection-preview--n9qwqd0ef) · Visual Studio Code · 1 upvotes · 0 comments --- Tags: [#github](https://daily.dev/tags/github), [#llm](https://daily.dev/tags/llm), [#vscode](https://daily.dev/tags/vscode), [#ai-coding](https://daily.dev/tags/ai-coding), [#prompt-engineering](https://daily.dev/tags/prompt-engineering) [View this post on daily.dev](https://daily.dev/posts/how-we-ship-models-in-vs-code-live161-3fywc3ys9) ```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":"How we ship models in VS Code | LIVE161","url":"https://daily.dev/posts/how-we-ship-models-in-vs-code-live161-3fywc3ys9","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-we-ship-models-in-vs-code-live161-3fywc3ys9"},"datePublished":"2026-06-05T13:57:15.616Z","dateModified":"2026-06-05T13:57:36.842Z","description":"A VS Code product manager explains the behind-the-scenes work required to ship new AI models in GitHub Copilot. Each model — even within the same family like...","image":"https://i.ytimg.com/vi/82WO6R--wxo/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/82WO6R--wxo/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Visual Studio Code","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":"Visual Studio Code","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/d5adab6ae9fb44d19859748fc30f5e18","url":"https://daily.dev/sources/vscode"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-we-ship-models-in-vs-code-live161-3fywc3ys9","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"github,llm,vscode,ai-coding,prompt-engineering","timeRequired":"PT16M","video":{"@type":"VideoObject","name":"How we ship models in VS Code | LIVE161","description":"A VS Code product manager explains the behind-the-scenes work required to ship new AI models in GitHub Copilot. Each model — even within the same family like...","thumbnailUrl":"https://i.ytimg.com/vi/82WO6R--wxo/sddefault.jpg","uploadDate":"2026-06-05T13:57:15.616Z","duration":"PT16M","url":"https://api.daily.dev/r/3FYWc3YS9","embedUrl":"https://www.youtube.com/embed/82WO6R--wxo"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Visual Studio Code","item":"https://daily.dev/sources/vscode"},{"@type":"ListItem","position":3,"name":"How we ship models in VS Code | LIVE161"}]} ```