jannikreinhard - Jannik Reinhard

Skills, MCP, CLI, Computer Use: Mapping the AI Tooling Surface in 2026

15. May 202615. May 2026 jannikreinhardLeave a comment

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.

Skills, MCP, CLI, Computer Use: Mapping the AI Tooling Surface in 2026 image 2

MICROSOFT 365 AGENTS EXPLAINED: WHA AGENTS 365 MEANS

Microsoft Agent 365 vs. Microsoft 365 Agents: A Field Guide for IT and Architects

5. May 20265. May 2026 jannikreinhardLeave a comment

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.

Microsoft 365 Agents: declarative agents, custom engine agents, and Agent Builder in the Microsoft Copilot host

Intune Policy Manager AI-powered policy descriptions and conflict analysis dashboard.

AI-Powered Intune Policy Documentation and Conflict Analysis

28. March 20265. May 2026 jannikreinhardLeave a comment

If you manage Microsoft Intune at scale, you know the pain: hundreds of policies, most of them with empty or outdated descriptions, and zero visibility into which settings overlap or even contradict each other across policies. I’ve seen this in pretty much every tenant I’ve worked with and honestly, it’s one of the most underestimated operational risks in modern endpoint management.

So I built a tool to fix it. It builds on the same idea I explored in Create your own Intune Co Pilot using Azure OpenAi Studio, but takes it further with policy documentation and conflict analysis. Let me walk you through it.

Intune policy management tool showing conflict analysis dashboard

CLI Tools vs MCP: Better AI Agents With Less Context

22. February 20265. May 2026 jannikreinhard1 Comment

Let’s be honest: MCP (Model Context Protocol) was supposed to be the universal connector between AI models and the real world. A clean, structured protocol that lets your AI agent talk to any tool through a standardized interface. Sounds great in theory. In practice? I’m increasingly reaching for good old CLI tools instead — and I’m not alone.

After months of building AI agent solutions and working with both approaches in real-world enterprise scenarios, here’s my take: CLI tools are the better choice in many cases, and the reason is surprisingly simple — context efficiency.

Terminal window showing AI agent command line tools

Azure AI Content Safety Guide: Filters and Best Practices

18. February 20265. May 2026 jannikreinhardLeave a comment

Azure AI Content Safety is Microsoft’s AI-powered service for detecting harmful content in both user-generated and AI-generated text and images. It runs as the built-in content filtering system for all Azure OpenAI and Foundry model deployments, screening both prompts and completions through an ensemble of classification models. The service is available as a standalone API and is deeply integrated into the Microsoft Foundry portal. It went through major expansion, adding prompt injection defense, hallucination detection, copyright protection, and PII filtering alongside its core harm-category classifiers.

In my opinion, Microsoft did a great job with this service.

Azure AI Content Safety dashboard with moderation categories

8 Productivity Tools I Use Daily for AI, Coding, and Planning

9. February 20265. May 2026 jannikreinhardLeave a comment

There’s a question I get asked very often: “What tools do you actually use every day?”

These are the ones I personally rely on to stay productive and creative — and if you use AI in your workflow too, my guide on prompt engineering is a good place to start.

So here it is – my complete daily toolkit, broken down by what each tool actually does for me and why I chose it over the alternatives.

Daily productivity tools and apps on a desk

Azure OCR Comparison: Mistral, GPT & Document Intelligence

12. January 20265. May 2026 jannikreinhard

Document Intelligence vs. Content Understanding vs. Mistral OCR 3 vs. GPT-5 vs. Azure Vision

Extracting data from documents is no longer just about “reading” text—it’s about intelligent understanding. Whether you’re digitizing 10,000 invoices, building a real-time app to read street signs, or preparing scientific papers for RAG pipelines, Azure offers a specialized toolkit within its Foundry ecosystem.

In this post, we’ll dive deep into performance, pricing, and capabilities of the leading OCR models in Azure—including the brand-new Mistral OCR 3 and VLM-based approaches with GPT-5.

Document OCR tools comparison with papers and AI icons

Build a Microsoft Intune AI Agent with Foundry

2. January 20265. May 2026 jannikreinhard3 Comments

We’ve all built PowerShell scripts to query Intune, wrapped them in some automation, and called it a day. It works. But with Azure OpenAI Service and models like GPT-4.1 and GPT-5.2 optimized for tool calling, there’s a more interesting approach—building an actual AI agent that can talk to your Intune environment.

Instead of writing a script for every query, you build one agent that understands natural language and calls the Graph API on your behalf. Ask it “which Windows devices are non-compliant?” and it figures out the right API call, executes it, and summarizes the results. It’s not magic—it’s function calling with a nice interface.

In this post, I’ll walk you through two different approaches to building this agent: the classic direct SDK approach and the newer Microsoft Agent Framework. Both use the same underlying Graph API client, but differ in how they orchestrate the AI. Let’s dive in.

How to Create an AI Selfie Tour Video with Tech Icons

21. December 20255. May 2026 jannikreinhard

This post shows you How to Create an AI Selfie Tour Video with Tech Icons — using a stack of generative AI tools to produce a polished short video that animates well-known industry figures into a single tour. I cover the prompts, the model choices, and the editing pipeline behind this AI Selfie Tour Video featuring Tech Icons.

Let’s be honest: the AI video space has exploded. Every week there’s a new tool promising Hollywood-quality results. But what happens when you combine AI image generation with video transformation and some creative editing? You get something that looks surprisingly real – and it’s easier than you might think.

I recently created a video that looks like I’m walking around, taking selfies with some of the most recognizable faces in tech. Sam Altman, Bill Gates, Steve Jobs – the whole crew. And no, I didn’t actually meet them at a conference. Here’s exactly how I did it.

Microsoft IQ Explained: Making Enterprise AI Agents Work

26. November 20255. May 2026 jannikreinhard

This post is a practical explanation of Microsoft IQ — the intelligence layer that finally makes enterprise AI agents work in production. I cover what IQ is, where it sits in the Microsoft AI stack, and how it changes the way IT admins design and deploy AI agents grounded in tenant data.

How Microsoft IQ Makes Enterprise AI Agents Work

Diagram of Microsoft IQ intelligence layer for AI agents

Let’s be honest: building AI agents in the enterprise has been a mess. You spend 80% of your time stitching together data sources, wrestling with RAG pipelines, and praying your agent doesn’t hallucinate the CEO’s name. Every new project feels like reinventing the wheel – but a wheel made of duct tape and hopes.

At Ignite 2025, Microsoft dropped something that might actually change this. They call it “IQ” – a unified intelligence layer that spans across Microsoft 365, Fabric, and Microsoft Foundry. And no, it’s not just another buzzword. If you’ve been experimenting with smaller Foundry use cases, like a paperless-office document manager, this is the enterprise-scale version of that same idea. Let me break down what this actually means for you.

Microsoft Intune & AI Insights

Author: jannikreinhard