This category collects all tutorials and guides by Microsoft MVP Jannik Reinhard about AI for IT admins, endpoints, and the enterprise.
AI for IT admins, endpoint engineers and the modern enterprise. This category collects every hands-on article on this blog about applying artificial intelligence to real-world IT and endpoint management problems — from Microsoft Copilot and Azure OpenAI, to custom GPTs, Microsoft Foundry agents, RAG architectures and AI-driven Intune tooling.
You’ll find practical guides on building your own Intune AI agent, using Azure AI Search for grounded retrieval, deploying Azure AI Content Safety in production, comparing OCR engines (Mistral, GPT, Document Intelligence) for paperless workflows, and learning the prompt engineering patterns that separate prototypes from production-grade AI features. Every post includes architecture diagrams, code examples, and the operational considerations Microsoft MVPs care about — security, governance, cost, and explainability.
If you are an IT admin starting your AI journey, a developer integrating LLMs into endpoint workflows, or a CISO evaluating where generative AI belongs in your stack, this is the place to start. New articles are added several times per month — based on what I’m currently shipping at Epic Fusion as Head of AI.
In this blog post I explain how to run AI models completely offline on a Mac with Microsoft Foundry Local. No Azure subscription, no API key, no internet connection. Everything runs on your own device.
I made a short video that walks through the whole thing. If you prefer watching over reading, here it is:
The rest of this post is the written version, so you can copy the commands and follow along.
Read More »
If you have sat through a Microsoft keynote more than once, you know the pattern: a wall of product names, a couple of demos that feel like magic, and then weeks of work figuring out what is actually shipping versus what is a sizzle reel. Build 2026 (San Francisco, June 2–3) was the most agent-dense keynote Microsoft has ever given — seven in-house models, a whole context layer, a brand-new category of agent, a containment story that reaches from silicon to cloud, and a concept for hardware that runs agents instead of apps.
This post is the map I wish I’d had on the morning of June 2. I’ll walk every major announcement, explain each one the way I’d explain it to a colleague (not the way the press release phrases it), and — because that’s the job most of us actually have — call out what it means for whoever has to deploy, govern and secure this stuff. It is a round-up, not a feature comparison, and I’ll flag clearly what is generally available, what is preview, and what is still just a slide.
Read More »
If you have built more than one AI tool in the past twelve months, you have noticed the same thing I have: the surface area of “how a model talks to systems” has exploded. Skills, MCP servers, CLI tools, Computer Use, function calling, declarative agents, custom engine agents, apps, actions, extensions, gems — every vendor uses a slightly different word for what looks like the same thing on a marketing slide. They are not the same thing. The trade-offs are real, the choice changes architecture, and picking the wrong one wastes weeks.
This post is the mental model I now apply by default when I sit down to build something agentic. It is opinionated. It is not a feature comparison. The goal is to help you decide which surface to reach for first, not to memorise the spec of each one.
I’ll cover seven surfaces (the original five, plus two that are too important to skip in 2026), map them across Anthropic, OpenAI, Microsoft, and Google terminology, and give you the decision tree I actually use.
Microsoft Agent 365 vs. Microsoft 365 Agents is the field guide distinction for IT teams and architects: one term describes governed agent operations, while the other describes the agents users build and run inside Microsoft 365 experiences.
If you’ve spent the last twelve months in the Microsoft AI ecosystem, you’ve watched the same pattern repeat: every announcement reframes the same thing under a slightly different banner. Copilot. Copilot Studio. Microsoft Foundry. Microsoft Agent Framework. Declarative agents. Custom engine agents. And now, two terms that sound almost identical but mean very different things Microsoft 365 Agents and Microsoft Agent 365.
I keep seeing them used interchangeably, including in serious technical posts. They are not interchangeable. With Agent 365 hitting general availability on May 1, 2026, getting this distinction right is no longer a pedantry exercise it’s a procurement, governance, and architecture decision.
This post is the version I would have wanted before I started building.
Endpoint management has come a long way from the days of manual, on-premises processes. In today’s world where employees work from home, on the road, or in branch offices, IT teams need tools that are not only powerful but also flexible and intelligent. Microsoft’s journey from Configuration Manager (SCCM) to Intune, and now toward AI-driven automation, shows how we can bridge legacy systems with cloud innovation to deliver seamless, secure, and proactive device management.
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 hundreds of agents, prompts, and AI conversations, and the structures I now apply by default.
Welcome to the future, where chatting with AI is as common as texting a friend! But just like crafting the perfect message to your crush, getting the right response from AI requires a bit of finesse. Enter the world of prompt engineering.
In diesem Sponsor-Artikel gehe ich Robopack A bis Z durch — alles, was du wissen musst, um zu entscheiden ob das Tool in deinen Microsoft-Intune-Stack passt. Was leistet Robopack, wo sind die Grenzen, und wie sieht ein realistischer Rollout in einem produktiven Tenant aus?
Application packaging is one of the most thankless jobs in endpoint management — until something goes wrong, nobody notices it, and the moment it does, everyone notices. Robopack entered this space promising a fundamentally different approach: AI-assisted packaging that turns hours of MSI repackaging and silent-install detective work into a guided workflow. In this post I walk through Robopack from A to Z — what it actually does, where it fits in a Microsoft Intune tenant, how the pricing maps to a real fleet of devices, and the situations where I would (and would not) reach for it. Sponsored review, but the technical assessment is mine and any limitation I hit is in here too.
In meinem ersten deutschen Blogpost heiße ich dich willkommen zu meiner neuen Robopack-A-bis-Z-Serie! In dieser dreiteiligen Videoserie gehe ich detailliert auf die wichtigsten Funktionen und Einsatzmöglichkeiten von Robopack ein – einem leistungsstarken Tool für dein Application Management.
Read More »
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 up semantic ranking and vector search, the workflow here is the same one I use to build production-grade AI search for real workloads.
The Azure AI search is one of the most powerful search engines at least in my experience. In times of AI and LLMs, the previously boring technology of search engines is now experiencing a new hype. In this blog post, I’ll guide you through deploying and configuring Azure AI Search, and show how it can transform your data into a highly searchable, AI-enhanced resource.
Read More »
In this short blog I want to show you how you can use GPT to get a summarization of the Intune Management Extension log. This script will read the Intune Management Extension Log file in the ProgramData/Microsoft/IntuneManagementExtension/Logs folder and will pass the latest content of the log to GPT.
