Microsoft for Developers
Get the latest information, insights, and news from Microsoft.
Latest posts
Your AI coding agent evaluation is only as good as its sandbox
Your AI coding agent passed the eval. But did the model know the answer, or did it find it somewhere on your machine? A correct answer can still invalidate your measurement.
Build an interview coach app with the GitHub Copilot SDK
An interview coach has to do more than ask questions. It needs to read a resume, follow up on an incomplete answer, and save enough context to give useful feedback at the end. Some of that work is conversation. Some of it requires calling an application service. The GitHub Copilot SDK lets you use the runtime behind Copilot CLI for that work inside your own application. You provide instructions and callable tools. Copilot handles the model interaction and resulting tool calls, while your application owns the interface and business workflow. For a developer building a personal assistant or an internal workflow, ...
Your work might not need the smartest model
The smartest model can cost five times more and deliver the same result, or even a worse one. See how evaluating your own work helps you get more value from your agent budget.
Start here: Azure SQL Foundations series
Most developers I talk to aren't asking whether Azure SQL Database can handle their next app. They're asking where to start when it comes to modernization, migration, and AI in the database. If you're reading this, you're probably in a similar boat: you've got an existing schema or databases, a scaling question you haven't had to answer yet, and a growing list of AI features you're expected to have an opinion about. That's why we built the path we kept describing in calls, with customers, and in the community. The Azure SQL Database Foundations series are four videos that take you from your first Hyperscal...
Try Azure SRE Agent with no always-on charges
We are happy to announce a 30-day trial experience for Azure SRE Agent. New customers can create and configure the SRE Agent at their own pace, with no charges for setup time or keeping agents ready. During the trial, you can connect your agents to telemetry, source code, incident management platforms, and other operational tools, and pay only for the Azure Agent Units (AAUs) consumed when your agents perform work. We are also excited to share the GA of Azure SRE Agent VNet integration and the Public Preview of Live Reports. With VNet support, the agent operates under your existing network controls, so it can ...
The Microsoft 365 Copilot Agent’s Playbook: A Practical Livestream Series for Building Better Agents
Building on Microsoft 365 Copilot? Here's your playbook. Declarative agents are quickly becoming one of the most exciting ways to extend Microsoft 365 Copilot and bring organizational knowledge, workflows, and tools directly into the flow of work. But as agent capabilities grow, so does the need for practical guidance: How do you build agents that are useful, grounded, extensible, and measurable? That’s why we’re launching The Microsoft 365 Copilot Agent’s Playbook, a four-part livestream series designed to help developers, makers, and technical teams understand how modern Microsoft 365 Copilot decl...
How to test agent experience changes without shipping them
Most changes you think will improve AI agent behavior won't. We tested a dozen hypotheses on a real project upgrade scenario and the majority failed. Learn how to emulate documentation, API, and MCP server changes locally so you can validate what works before shipping anything to production.
How to test agent skills without hitting real APIs
Your agent skill calls an API. The moment you start evaluating it, every run either costs money or mutates production data. Learn how to mock APIs transparently so you can run evals without changing your skill or hitting real endpoints.
Building AX evals that actually work
This is the eighth and final article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can't control in the agent stack, how to measure whether your extensions are helping or hurting, and how to iterate toward better outcomes. You've read seven articles about what to measure, why benchmarks don't transfer, and what hidden variables can do to your results. Now you actually have to build the thing. Most teams build an eval, run it, get scores, and feel good about the numbers. The trouble is that these evals produ...