Setting up Azure Chat is now as simple as running these Azure CLI commands:
1. Initialise: azd init -t microsoft/azurechat
2. Deploy: azd up
Hopefully @savostrowski is proud of AZD UP as we are!
https://t.co/yJTKcyrO4Z
#ai#azureopenai#openai#azureai#azurechat
Check out these apps built by MAI-Code-1-Flash in VS Code. MAI-Code-1-Flash is optimized for GitHub Copilot for day-to-day development tasks. It now starts rolling out to GitHub Copilot individual users in VS Code. Let us know your feedback: https://t.co/WwQMSRfwrI
Announced at #MSBuild2026! Azure Cosmos DB Semantic Reranker, Agent Memory Toolkit, Linux Emulator, and more! Get the scoop on everything we announced today at Build and what's still to come this week.
https://t.co/gD9ub4Z0kg
#MSBuild#AzureCosmosDB#AIApps
🚨 MAI-Image-2.5 is now live on fal!
📸 Photorealistic images with natural lighting and accurate skin tones
Refined text rendering for branding, packaging, and commercial design
Text-to-image and image editing with precise, design-ready control
We believe the agent harness in @code to be best in market today.
Today, the team shared a behind-the-scenes look at our harness optimization efforts, including our own offline evaluation suite vsc-bench:
https://t.co/NiG58H6fH8
@jeffhollan look at that! Got @mastra working inside Foundry Hosted Agents! Mastra supports Responses API by default so wasn't too hard to implement it.
Still need to give it a full try of all Mastra features though.
Here's another reason why @Microsoft Foundry is the BEST platform in the world to build and run your agents: Our durable, long running agents come with Toolbox 🔨
Toolbox allowed me to reduce input tokens 90%(!!) and significantly simplify the amount of code needed
Check out the demo below and see how you can bring hundreds of tools through a single MCP endpoint -- all running in Foundry at cloud scale! ☁️
With the upcoming move to usage-based billing, the @code team has been working on a number of initiatives to improve the token efficiency of our harness while not hindering the quality of the agent, including:
- Prompt caching improvements
- Tool search tool
- New tools for search and execution
More here: https://t.co/uvPZaJv57q
Microsoft's MIT licensed VibeVoice speech-to-text model (think Whisper with speaker diarization) is really good - my notes on running the 5.71GB 4bit MLX conversion on an M5 MacBook, using about 60GB of RAM at peak and transcribing 1hr of audio in ~9 mins https://t.co/lyu5rtXwPQ
Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see.
@eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)
Thanks to Prime Minister @AlboMP for the warm welcome today.
We are making our largest investment in Australia to date, committing A$25 billion to expand AI and cloud capacity, strengthen cybersecurity, and help people and organizations across the country build digital skills.
Three ways to author .NET agent skills — file, class, or inline — all running through one provider. Add script execution + human approval and you’ve got a flexible, governed skill model for real apps.
Blog: https://t.co/ZgtfK0ezzy