--- title: Azure Update 14th August 2026 | daily.dev description: Weekly roundup of Azure platform updates covering compute, networking, storage, and AI. App Service gains preview markdown support for AI agent consumption;... canonical: https://daily.dev/posts/azure-update-14th-august-2026-bcqivtmbi twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Azure Update 14th August 2026 | daily.dev og:description: Weekly roundup of Azure platform updates covering compute, networking, storage, and AI. App Service gains preview markdown support for AI agent consumption;... og:url: https://daily.dev/posts/azure-update-14th-august-2026-bcqivtmbi og:image: https://api.daily.dev/og/posts/bcQiVtmbi.png og:image:alt: Azure Update 14th August 2026 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. # Azure Update 14th August 2026 **[John Savill's Technical Training](https://daily.dev/sources/john-savill)** · 7 min read · 0 upvotes · 0 comments ## Summary Weekly roundup of Azure platform updates covering compute, networking, storage, and AI. App Service gains preview markdown support for AI agent consumption; AKS control plane metrics via Prometheus reach GA; ExpressRoute Resiliency Guard enters preview; Azure Firewall Premium throughput doubles to 22 Gbps; Front Door adds atomic batch rule updates (GA) and mutual TLS (preview); shared premium SSDv2 and ultra disks support dynamic resizing; Fabric adds default item-level recovery from August 23rd; Postgre SQL gets GA pre-upgrade validation. Also covers new Microsoft AI model releases: MAI coding model 1.1 in GitHub Copilot (25% fewer tokens, 25% faster, quarter of the cost), a new image model, Microsoft's first reasoning model in Foundry (35B active of 1T total parameters, MoE, 256K context), and Gemini 3.7 Flash arriving in GitHub Copilot. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What does the MAI coding model 1.1 update in GitHub Copilot improve over the previous version? The MAI coding model 1.1 in GitHub Copilot uses 25% fewer tokens to complete a task, streams tokens 25% faster, and costs a quarter of the previous version, while delivering higher quality output. It reflects an iterative improvement cycle sometimes called hill climbing, where a model is shipped, evaluated, and refined repeatedly. _daily.dev helps developers track coding model updates like this before switching their Copilot workflow._ ### How does Azure App Service markdown support help reduce tokens for AI agents? Azure App Service can automatically convert an app's HTML-formatted response into markdown when the requesting client adds an accept text/markdown header, and this feature is in preview for Windows instances with Linux support coming. Markdown has lower formatting overhead than HTML, which reduces the token count AI agents need to process the content. _Developers building AI agents that consume web content can follow infrastructure changes like this on daily.dev._ ### What are the specs of Microsoft AI's first reasoning model released in Foundry? The first Microsoft AI reasoning model, called thinking, is a medium-sized mixture-of-experts model with 35 billion active parameters out of 1 trillion total, built on clean traceable data with no distillation from another model. It has a 256,000-token context window, roughly a 600-page document, and benchmarks similarly to Claude Opus 4.6. _daily.dev keeps developers comparing new reasoning models like this ahead of picking one for production._ --- Tags: [#cloud](https://daily.dev/tags/cloud), [#github](https://daily.dev/tags/github), [#azure](https://daily.dev/tags/azure), [#networking](https://daily.dev/tags/networking) [View this post on daily.dev](https://daily.dev/posts/azure-update-14th-august-2026-bcqivtmbi) ```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":"Azure Update 14th August 2026","url":"https://daily.dev/posts/azure-update-14th-august-2026-bcqivtmbi","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/azure-update-14th-august-2026-bcqivtmbi"},"datePublished":"2026-08-14T15:32:38.495Z","dateModified":"2026-09-13T19:57:16.331Z","description":"Weekly roundup of Azure platform updates covering compute, networking, storage, and AI. App Service gains preview markdown support for AI agent consumption;...","image":"https://i.ytimg.com/vi/KPNPsO-72Kw/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/KPNPsO-72Kw/sddefault.jpg","isAccessibleForFree":true,"articleSection":"John Savill's Technical Training","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":"John Savill's Technical Training","logo":"https://media.daily.dev/image/upload/s--4rApg0fT--/f_auto,q_auto/v1780213220/logos/john-savill?_a=BAMAMiWQ0","url":"https://daily.dev/sources/john-savill"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/azure-update-14th-august-2026-bcqivtmbi","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"cloud,github,azure,networking","timeRequired":"PT7M","video":{"@type":"VideoObject","name":"Azure Update 14th August 2026","description":"Weekly roundup of Azure platform updates covering compute, networking, storage, and AI. App Service gains preview markdown support for AI agent consumption;...","thumbnailUrl":"https://i.ytimg.com/vi/KPNPsO-72Kw/sddefault.jpg","uploadDate":"2026-08-14T15:32:38.495Z","duration":"PT7M","url":"https://api.daily.dev/r/bcQiVtmbi","embedUrl":"https://www.youtube.com/embed/KPNPsO-72Kw"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"John Savill's Technical Training","item":"https://daily.dev/sources/john-savill"},{"@type":"ListItem","position":3,"name":"Azure Update 14th August 2026"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/azure-update-14th-august-2026-bcqivtmbi#faq","mainEntity":[{"@type":"Question","name":"What does the MAI coding model 1.1 update in GitHub Copilot improve over the previous version?","acceptedAnswer":{"@type":"Answer","text":"The MAI coding model 1.1 in GitHub Copilot uses 25% fewer tokens to complete a task, streams tokens 25% faster, and costs a quarter of the previous version, while delivering higher quality output. It reflects an iterative improvement cycle sometimes called hill climbing, where a model is shipped, evaluated, and refined repeatedly. daily.dev helps developers track coding model updates like this before switching their Copilot workflow."}},{"@type":"Question","name":"How does Azure App Service markdown support help reduce tokens for AI agents?","acceptedAnswer":{"@type":"Answer","text":"Azure App Service can automatically convert an app's HTML-formatted response into markdown when the requesting client adds an accept text/markdown header, and this feature is in preview for Windows instances with Linux support coming. Markdown has lower formatting overhead than HTML, which reduces the token count AI agents need to process the content. Developers building AI agents that consume web content can follow infrastructure changes like this on daily.dev."}},{"@type":"Question","name":"What are the specs of Microsoft AI's first reasoning model released in Foundry?","acceptedAnswer":{"@type":"Answer","text":"The first Microsoft AI reasoning model, called thinking, is a medium-sized mixture-of-experts model with 35 billion active parameters out of 1 trillion total, built on clean traceable data with no distillation from another model. It has a 256,000-token context window, roughly a 600-page document, and benchmarks similarly to Claude Opus 4.6. daily.dev keeps developers comparing new reasoning models like this ahead of picking one for production."}}]} ```