--- title: WWDC26: Improve your prompts by hill-climbing with... description: Apple's WWDC26 session introduces the Evaluations framework and the hill-climbing process for iteratively improving AI-powered app features. The talk walks... canonical: https://daily.dev/posts/wwdc26-improve-your-prompts-by-hill-climbing-with-evaluations-apple-muzy3xxlz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: WWDC26: Improve your prompts by hill-climbing with Evaluations | Apple | daily.dev og:description: Apple's WWDC26 session introduces the Evaluations framework and the hill-climbing process for iteratively improving AI-powered app features. The talk walks... og:url: https://daily.dev/posts/wwdc26-improve-your-prompts-by-hill-climbing-with-evaluations-apple-muzy3xxlz og:image: https://api.daily.dev/og/posts/muZY3XxLZ.png og:image:alt: WWDC26: Improve your prompts by hill-climbing with Evaluations | Apple 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. # WWDC26: Improve your prompts by hill-climbing with Evaluations | Apple **[Apple Developer](https://daily.dev/sources/appledeveloper)** · 26 min read · 0 upvotes · 0 comments ## Summary Apple's WWDC26 session introduces the Evaluations framework and the hill-climbing process for iteratively improving AI-powered app features. The talk walks through a Book Tracker app example, demonstrating how to measure tag quality using relevance and usefulness score dimensions, detect and fix judge-human drift using Cohen's kappa coefficient, and run comparative evaluations in Xcode 27. Key takeaways include treating each iteration as a controlled experiment, changing one variable at a time, aligning model judges to expert human ratings, and expanding improvements beyond prompts to tools and models. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#llm](https://daily.dev/tags/llm), [#ios](https://daily.dev/tags/ios), [#prompt-engineering](https://daily.dev/tags/prompt-engineering) [View this post on daily.dev](https://daily.dev/posts/wwdc26-improve-your-prompts-by-hill-climbing-with-evaluations-apple-muzy3xxlz) ```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":"WWDC26: Improve your prompts by hill-climbing with Evaluations | Apple","url":"https://daily.dev/posts/wwdc26-improve-your-prompts-by-hill-climbing-with-evaluations-apple-muzy3xxlz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/wwdc26-improve-your-prompts-by-hill-climbing-with-evaluations-apple-muzy3xxlz"},"datePublished":"2026-06-08T21:25:23.133Z","dateModified":"2026-06-08T21:33:35.375Z","description":"Apple's WWDC26 session introduces the Evaluations framework and the hill-climbing process for iteratively improving AI-powered app features. The talk walks...","image":"https://i.ytimg.com/vi/sNDkT9mYDTQ/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/sNDkT9mYDTQ/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Apple Developer","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":"Apple Developer","logo":"https://media.daily.dev/image/upload/s--CAtMViBl--/f_auto/v1711726806/logos/appledeveloper","url":"https://daily.dev/sources/appledeveloper"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/wwdc26-improve-your-prompts-by-hill-climbing-with-evaluations-apple-muzy3xxlz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ios,prompt-engineering","timeRequired":"PT26M","video":{"@type":"VideoObject","name":"WWDC26: Improve your prompts by hill-climbing with Evaluations | Apple","description":"Apple's WWDC26 session introduces the Evaluations framework and the hill-climbing process for iteratively improving AI-powered app features. The talk walks...","thumbnailUrl":"https://i.ytimg.com/vi/sNDkT9mYDTQ/sddefault.jpg","uploadDate":"2026-06-08T21:25:23.133Z","duration":"PT26M","url":"https://api.daily.dev/r/muZY3XxLZ","embedUrl":"https://www.youtube.com/embed/sNDkT9mYDTQ"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Apple Developer","item":"https://daily.dev/sources/appledeveloper"},{"@type":"ListItem","position":3,"name":"WWDC26: Improve your prompts by hill-climbing with Evaluations | Apple"}]} ```