Coming soon, GitHub Copilot will determine when a task is best handled by on-device intelligence and when it should leverage cloud-scale models.

Many AI calls are not really conversations. A support message needs an intent. A workflow needs a route. A policy check needs a yes or no. An agent needs to...

Build Agentic UI with the new Blazor AI components for streamed content, tools, approvals, shared state, and generative experiences.

Microsoft’s Autopilots mark a shift from AI that responds to prompts to persistent agents with identity, initiative and standing responsibilities. As AI...

The operating model for AI agent governance is evolving. See three ways IT admins can start upleveling the way their organization governs their agent estate.

AI models are increasingly taking on work that extends far beyond a single prompt: building a feature across a codebase, investigating a complex issue,...

Learn about the latest announcements from the AKS team around workload and AI isolation, AI agents, and efficiency.

AI agents become operationally interesting when they can reach real systems. They also become operationally dangerous at exactly the same moment. Caldova...

A common question that we get from our customers is "Hey guys, we are excited about SRE agent and we 've created one but whats the best way to configure...

Dynamic workflows are now available in Copilot CLI, the GitHub Copilot app, and the GitHub Copilot SDK. These let you define an orchestration in code to get the reliability and…

In controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline while reducing estimated cost.

Explore GPT-6 Astra, Sol, and GPT-6 Luna in Microsoft Foundry, with scalable model options for production AI agents, complex workflows, and high-volume tasks.

If you have been hearing the term “MCP server” everywhere and quietly nodding along without fully getting it — this post is for you. My goal is simple: by...

Learn how Microsoft Foundry is connecting agents with enterprise knowledge, supporting long-running execution, and applying governance.

September 2026. Views are my own, not Microsoft guidance. Pricing and product behavior change fast: everything below is accurate at time of writing. Verify...

Using as a reference of this article. Automating Azure SQL DB index and statistics maintenance using Azure Automation | Microsoft Community Hub To provide...

Azure Virtual Machine Scale Sets (VMSS) are useful when an application needs to run across multiple virtual machines while automatically scaling based on...

Modern application development increasingly relies on AI agents to generate code, configure services, and accelerate delivery. But generic agents often stop...

TL;DR: Azure Managed Redis has no capacity-reporting API. This PowerShell poller safely rotates real creation attempts across approved regions and SKUs until...

Azure Functions already gives you a familiar way to build event-driven apps. A queue message, HTTP request, timer, or event triggers the code that handles...

Azure Functions Flex Consumption now supports site-scoped TLS certificates and end-to-end TLS encryption for custom domains, mTLS, and secure serverless apps.

Learn when to use Flex processing, send Flex requests, implement a Standard fallback, and monitor usage and costs for Azure OpenAI.

Azure Functions can already connect to many Azure services through triggers and bindings. With managed connectors, your functions can access about 1,700...

Business Scenario A retail organization runs multiple promotional sales events across its store network in different cities, featuring various product...

Introduction Enterprise agents become more valuable when they can securely access the data, knowledge and business systems organisations already rely on....

Learn how to design zone-resilient Azure workloads by choosing the right availability zone strategy for each component, balancing reliability, cost, and operational complexity.

Where reusable pipelines start to hurt Who this is for: Platform and DevOps engineers who build shared Azure DevOps Pipeline Templates and want other teams...

Introduction — The Monday morning bundle Imagine a case manager opening a new request on Monday morning. The case is not represented by one neat digital...

Difficulty: Intermediate A support email arrives with a product name, an error code, and a country. Before anyone can help, someone has to interpret...

What orchestration changes Media workflows are already distributed across specialized creative, content, rights, archive, delivery, audience, and...

Keep your domain services distributed. Move the specialist's instructions, not another model, into the orchestrator. A multi-agent system often starts

Tamara Gaidar, Senior Data Scientist, Microsoft Security Research Team Maor Nissan, Principal Data Scientist, Microsoft Security Research Team About this...

Introduction AI agents are rapidly becoming a core component of enterprise transformation strategies. Organizations are deploying agents to assist...

From AI Foundations to a Shared Operating Model In my previous article, AI Azure Landing Zone: Shared Capabilities and Models to Enable AI as a Platform, I...

Imagine you are building a home design application. A customer says, “Show me a modern kitchen with dark cabinets and a large center island.” Images appear...

Use AI coding agents with the Azure Cosmos DB vNext emulator to create resources, load test data, run queries, and speed up local development.

The Standard harness and GitHub Copilot harness are two authoring and runtime options within Microsoft Copilot Studio. A harness is the operating layer...

September 3, 2026 - AI can generate thousands of lines of code in minutes. Understanding what it changed across your application, and whether it is ready to...

Overview Every engineering team runs into the same wall: the code is written, the tests are green, and then the pull request sits, waiting for a human to...

A key benefit of Azure HorizonDB  comes from its smart storage layer, which works seamlessly with Postgres and takes over durability and high...

Subscribe to Microsoft Azure today for service updates, all in one place. Check out the new Cloud Platform roadmap to see our latest product plans.

In Azure Batch, customers running long tasks on Linux (Ubuntu) compute nodes sometimes observe that a task is interrupted and automatically...

Fable 5.1 and Mythos 5.1 are the same underlying model. Claude Fable 5.1 is a public preview version with safeguards that fallback for cyber and bio...

Discover how Microsoft Foundry helps optimize AI agents with context engineering, reducing token costs while improving quality, memory, and more.

Every app built on an LLM will eventually move to a new model. The model you shipped may be retired, or a newer model may offer better quality, cost, or...

Migrating an existing Windows application to the cloud can be challenging when it depends on server roles, local storage, registry access, or third-party libraries. If technologies such as…

A user submits a ticket: "Please grant temporary admin access to the finance reporting database for month-end close." A five-agent system handles it...

I got asked a question a few weeks ago that sounded simple. Lock down Azure AI Foundry with Private Link, and let the agents call an MCP server hosted on a...

Discover Inside Microsoft Foundry: Quickstart, a new video series for developers building AI agents. Starting with "What does it really take to ship an AI...