Microsoft Intune & AI Insights
In this blog post I show you how to run Claude Code inside your GitHub pipelines. With the official GitHub Action you can answer @claude mentions in issues, review every pull request automatically, and automate recurring standard tasks like reports or issue triage.
In this blog post I explain how multi-agent orchestration works in Microsoft Foundry today. I show why connected agents and portal workflows are going away, how the Microsoft Agent Framework patterns work, and which orchestration pattern I would pick for which scenario.
I show how my agentic operating system connects Notion, Outlook, Codex, OneDrive, GitHub, reusable skills and schedules with human review.
In this blog post I take a look at the Security Copilot agents in the Intune admin center. I explain what the Policy Configuration Agent, the Change Review Agent, and the new Vulnerability Remediation Agent do and how you can enable them. I also cover the licensing that gives Microsoft 365 E5 and E7 tenants included Security Copilot capacity.
A beginner-friendly Microsoft Foundry model deployment guide: choose a model, name the deployment and test the right fit before an app uses it.
In this blog post I take a deep look at Foundry IQ, the knowledge layer in Microsoft Foundry. I explain how knowledge bases and agentic retrieval work, how to connect them to an agent via MCP, and what this replaces from the classic RAG world.
A beginner-friendly Microsoft Foundry setup: create a project, understand models and deployments, then run one focused first test.
Since June 2026, Intune enforces Multi Admin Approval on app-authenticated Microsoft Graph API calls. In this blog post I explain why your automation now gets 403 errors, how the approval flow works for API calls, and how to use the new Exclusions tab for your automation apps.
In this blog post I explain how observability works for AI agents in Microsoft Foundry: zero-code tracing with OpenTelemetry, the monitoring dashboard, continuous evaluation on live traffic and alerts. With the exact setup I use in production.
Talk to live screen information with a Microsoft Foundry Realtime voice agent. Share an Azure page, ask by voice, and receive an immediate spoken answer.
In this blog post I explain the new auto-update feature of Enterprise App Management, which is generally available since the June 2026 service release. I show you how to enable it, how it compares to manual Win32 supersedence and winget, and which limitations you should know before you turn it on.
Migrate from the deprecated Azure AI Inference SDK to OpenAI v1 before 26 August 2026. Find old clients, update the endpoint and validate the deployment.
In this blog post I take a deep look at the model router in Microsoft Foundry and the model catalog behind it. I explain how routing works, what it costs, which deployment types exist and how I pick models for agents.
Microsoft Foundry June 2026 added Claude, agent publishing, Toolboxes, Routines and Memory. I explain the changes and build a practical Intune example.
In this blog post I explain how I secure Microsoft Foundry end to end: private networking for agents, Entra Agent ID and RBAC, customer-managed keys and guardrails. Written from an IT admin perspective, with the traps I ran into.
Microsoft now offers two big platforms for building AI agents: Microsoft Foundry and Copilot Studio. In this blog post I explain in depth how both work, compare models, pricing, governance, and quality, and give you a clear decision guide — including why Foundry is often the faster path if you can code.
This is the first episode of my new unboxing series with Admin By Request. I explain what their Endpoint Privilege Management solution is, how temporary admin rights and per-process elevation work, and why the Frankfurt data center matters for European companies.
In this blog post I show how to evaluate AI agents in Microsoft Foundry. I go through the built-in evaluators, the evaluation wizard in the portal, a runnable SDK example, and how continuous evaluation keeps an eye on your agent in production.
In this blog post I explain what Agent Skills are and why they are becoming an open standard across AI tools. I also show step by step how you can build your first own skill with a simple SKILL.md file.
In this blog post I show you how to build your first AI agent in Microsoft Foundry. We create a project, deploy a model, build the agent in the portal, test it in the playground, and call it from Python. At the end you have a working agent you can extend for your own scenarios.
AI agents like Claude Code and Copilot CLI run with your privileges. See how AI agent runtime protection in Defender for Endpoint blocks prompt injection.
Service Endpoints vs Private Endpoints, explained simply — where VNet Integration fits, and when to use an NSG, Azure Firewall or WAF. With diagrams.
In this blog post I explain how Microsoft Intune really works under the hood on Windows — including the new MMP-C and Declared Configuration channel — where every log lives, the tools I use, and a clear method to fix the errors you hit most. A deep A to Z guide.
A plain, hands-on look at the latest AI models in June 2026 — OpenAI, Anthropic, Google, Microsoft MAI, Mistral and the Chinese open-weight models. I sort them by price, capability and use case, and I explain what it means for European companies and data sovereignty.
How to run AI models fully offline on a Mac with Microsoft Foundry Local — no Azure, no API key, no internet. Everything runs on your own device.
A fact-based look at Intune Advanced Analytics from someone who ran AIOps in a large enterprise — what it does, how it works, and how it really compares.
Build 2026 was not a feature update — it was Microsoft declaring the agentic era a platform. Here is every major announcement, explained in plain language, with what it actually means for the people who have to run, secure and manage it.
A hands-on review of the Oakywood Standing Desk Pro — and why it actually improved my daily setup and productivity.
Skills, MCP servers, CLI tools, Computer Use, function-calling, declarative agents — the AI tooling surface has multiplied. Here is the mental model I use to decide which one to reach for, with the trade-offs I actually pay for in production.
Microsoft 365 Agents — the official term for the agentic platform inside the Microsoft 365 stack — moves AI from chatbox to autonomous worker. Here is the practical view from an endpoint admin and Microsoft MVP for both Intune and Foundry.
Discover an open-source Microsoft Intune tool using Azure OpenAI to generate policy descriptions and detect conflicts across your tenant.
Why CLI tools often outperform MCP for AI agents: less context overhead, learned commands, and better composability.
Azure AI Content Safety explained: configure harm filters, Prompt Shields, groundedness, protected material and production guardrails in Microsoft Foundry.
My daily productivity toolkit: Akiflow, Raindrop, Claude, Codex, Bitwarden and more tools that keep work simple and focused.
Compare Azure OCR tools—Document Intelligence, Content Understanding, Mistral OCR, GPT-4o and Vision—for smarter document AI.
Build an AI agent for Microsoft Intune with Azure OpenAI, GPT tool calling, and Graph API—compare Direct SDK vs Agent Framework.
Learn how I created realistic AI selfie videos with tech icons using Nanobanana, Artlist, and Canva in a simple one-hour workflow.
Microsoft IQ unifies Work IQ, Fabric IQ and Foundry IQ to give enterprise AI agents shared context, semantics and memory.
Discover DocumentManager, an open-source AI document management system with Azure OpenAI, OCR, semantic search, and auto-tagging.
Discover New Right Click Tools for SCCM, ConfigMgr, and Intune: automate patching, actionable reporting, and just-in-time privileged access.
Explore how Microsoft Intune, SCCM, AI automation, and Zero Trust are reshaping modern endpoint management for hybrid work.
Recast brings Right Click Tools to Intune with a free browser extension for faster co-managed device actions and compliance checks.
Simplify app management with Recast Application Workspace: automate patching, streamline deployments, and empower secure self-service.
To become a Prompt Engineering Pro in 2025 you have to master more than tricks — you have to master the art of talking to AI in a way that produces consistent results, especially when it comes to designing AI Conversations that scale. This post walks through the patterns that have worked for me across [ ]
Patch My PC Home Updater keeps Windows apps current for free. See the 2026 features, portable and MSI options, scheduling, requirements and security.
Convert Intune device groups to user groups—and vice versa—using Microsoft Graph PowerShell with this practical script.
Was kann Robopack für Intune? Mein gesponserter Praxistest zeigt Instant Apps, Robopatch, Deployment Waves, Radar, Setup und klare Grenzen.
This is only a small blog post but maybe for most of you very helpful, especially if you work a lot with Microsoft Graph. Often the problem is you want to run multiple calls and then you have to loop through the single items or have a long line of calls. The Microsoft Graph Batch [ ]
As an Intune MVP, I frequently need to test various setups on a dedicated test machine. The easiest way to do this is by building an Autopilot lab on MacOS using virtual machines (VMs). However, running a Windows VM on a MacBook Pro with Apple Silicon (M3) can be a bit tricky. In this blog [ ]
Azure AI Search: Build a Powerful AI Search Engine is the practical goal of this article: turning enterprise content into a searchable, ranked, and AI-ready knowledge layer with Microsoft Azure AI Search. This post is a hands-on guide to Build a Powerful AI Search Engine with Azure AI Search. From configuring the indexer to setting [ ]