Where Curiosity Meets Practice

Notes from real projects. What worked, what didn't, and why — no marketing spin.

Featured

Featured

Local AI Development with the Surface Laptop Ultra

Cloud AI is powerful, but every prompt costs tokens and your code leaves the building. A laptop that runs capable coding models on its own GPU changes that for everyday work. This setup runs the coding agent in a hybrid way: local coding models for daily development, cloud models when a task really needs them. And the numbers come from real measurements on the laptop, not from PowerPoint benchmarks.

Contact Center Intelligence one month in: what to prepare before the GA dates

Reflections on Contact Center Intelligence one month after the preview, and what architects should prepare before the general availability dates.

Agent FinOps in the Microsoft Ecosystem - Rev2

A living article on Copilot and agent costs. Where Copilot, Cowork, Copilot Studio, and Foundry agents show their costs, which controls actually stop spending, how to charge costs back, and what Microsoft has changed recently.

Understanding Microsoft Copilot Licensing - Rev2

A living article on what Copilot costs. What the Copilot license costs, how Copilot Credits work, which features use them, and what Microsoft has announced next.

Understanding Microsoft Power Platform Licensing Rev.7

A practitioner's reference for Power Platform core, Copilot Studio, Dataverse, Dynamics 365 Contact Center, and Dynamics 365 Customer Service.

Testing Copilot Agents: When to Use Agent Evaluation vs. the Copilot Studio Kit

On March 31, 2026, Microsoft launched Agent Evaluation in general availability, fundamentally changing how teams validate Copilot agents. This guide explains how Agent Evaluation and the Copilot Studio Kit serve different—but complementary—roles in your quality assurance strategy, and when to use each one.

Azure Local, Foundry Local, and Microsoft 365 Local: A Comprehensive Guide for IT Architects and Decision-Makers

Azure Local is Microsoft's distributed infrastructure solution that extends Azure capabilities to customer-owned environments. This article provides a comprehensive overview of Azure Local, Foundry Local, and Microsoft 365 Local, their use cases, deployment options, and best practices for IT architects and decision-makers considering on-premises Azure solutions. With an appendix on agentic AI use cases on Azure Local and Foundry Local.

Practical Guideline: How to Move Agents Beyond POCs and Deliver Real Enterprise Value

Discover ten core principles to transition AI agents from ideation to measurable business impact, including anchoring in real processes, maintaining scope discipline, integrating with live input channels, enforcing production-grade behavior, and planning for long-term flexibility.

Microsoft 365 E7: Why Microsoft's New License Is a Logical Step for Agent‑Driven Enterprises

Microsoft 365 E7, announced in March 2026, represents a strategic evolution of Microsoft's enterprise licensing to accommodate the rise of AI agents. This article explores what E7 includes, why it was created, and how it benefits organizations leveraging AI agents.

Introducing MATE: A Modular Testing Environment for AI Agents

As AI agents become integral to business processes, reliable and repeatable testing is essential for confidence in deployment. This article introduces the Multi-Agent Test Environment (MATE) – an enterprise-grade framework for automated testing of AI agents across platforms and frameworks – and explains how its modular design addresses key challenges in agent testing. We explore why testing AI agents is critical, delve into MATE's architecture and features, compare MATE with alternative testing approaches, and outline MATE's roadmap, including red-team testing, enhanced cloud deployment, and support for emerging agent frameworks.

Testing Copilot Studio Agents: Copilot Studio Kit vs. Agent Evaluation (Preview)

Choosing the right testing tool for your Copilot Studio agents: A detailed comparison of Copilot Studio Kit and Agent Evaluation (preview) to help you decide when to use each tool for optimal agent quality.

Hello, I’m Holger

I connect enterprise AI architecture with practical implementation, and share what I learn along the way.

I’m a Principal Architect at NTT DATA, Microsoft MVP and Microsoft Certified Trainer (MCT), based in Berlin. My work focuses on agentic AI, intelligent automation, and the Microsoft ecosystem. I help organizations move from promising demonstrations to secure, scalable, well-governed solutions. That means connecting technology choices with business processes, enterprise data, operational ownership, and measurable outcomes.

About me