Introduction Building AI agents that can actually do things in your business systems—create records, update opportunities, trigger workflows—typically requires weeks of custom integration work. The Dataverse MCP Server changes that. In this tutorial, you’ll connect a Microsoft Foundry agent to your Dataverse environment in under 30 minutes, giving your AI agent secure, real-time access to […]
Part 2 of a series. Part 1, Grounding Copilot Studio Agents with Azure AI Search and Foundry IQ, defined five grounding patterns. This article gives you a reproducible way to compare them without mixing latency boundaries, billing units, or quality signals. Reference implementation, not a production template. This article is for architects, agent developers, and
Benchmark Retrieval Patterns for Copilot Studio and Foundry IQ Continue Reading
A Real-World Scenario Imagine a customer support agent that answers invoice questions. During testing, everything works perfectly. But in production: The Finance API occasionally times out. The knowledge base contains outdated information. Tool calls fail during peak traffic. Token consumption rises unexpectedly. The result isn’t a broken AI model. It’s an unreliable system. This is
Building Production-Ready AI Agents in Microsoft Foundry: 10 Lessons Learned Continue Reading
The AI agent has moved from pilot project to production faster than most security programs were built to handle. Every AI agent you deploy is now a security problem before it is a productivity win. This Microsoft Agent 365 security deep dive breaks down exactly how the platform observes, governs, and secures agents in your
Hello Folks! It’s 3 a.m. Your phone lights up. A critical workload that spans multiple clouds is on fire, ownership is fuzzy, the alert routed to the wrong team first, and now it’s your problem. You sit up in bed, cold and groggy, and start the ritual. Open the runbook. Pull logs from one place.
From Alert to Resolved: Building a Self-Healing Azure Platform with SRE Agent Continue Reading
Remote Help lets your helpdesk team screen-share, chat with, and (with the right permission) take elevated control of a user’s session — including AVD multi-session hosts where several users can be active on the same VM at once. This is a two-part walkthrough. Part 1 covers enabling Remote Help at the tenant level and doing
Setting Up Microsoft Intune Remote Help on Azure Virtual Desktop Continue Reading
After working on many Azure SQL support cases, I have learned that the initial service request details are essential, although they may not always provide sufficient information to understand the complete technical situation. When a service request is initially created, the available information may be limited to a brief description such as: The database is
Reclaiming host pool capacity from disconnected sessions is one of those AVD hygiene tasks that’s easy to configure once by hand in Intune, and easy to forget to replicate consistently across every host pool, tenant, or DTAP environment you manage. If you’re standing up host pools programmatically — or you just want this baked into
In this post I go over some tools and techniques exist for hardening Windows Server. As always, apply controls according to the server’s role, test them against representative workloads before production rollout, document approved exceptions, and maintain tested console and recovery access in case a security control affects management or application compatibility. Apply the role-specific
Some tools and techniques for hardening Windows Server Continue Reading
Microsoft has released Windows Server vNext Preview Build 29621, and one feature stands out as a major step forward for on‑premises virtualization security: Trusted Launch for Generation 2 virtual machines. This capability, long familiar to Azure users, is now arriving in Windows Server for local Hyper‑V environments. What Trusted Launch Brings to Windows Server Trusted
Trusted Launch for virtual machines on Windows Server Insider Preview Continue Reading
