Notes from real projects. What worked, what didn't, and why — no marketing spin.
Microsoft is moving Claude processing in Microsoft Copilot into the EU Data Boundary by the end of 2026. Why that removes the strongest blocker for European tenants, why the decision still belongs to you, and how architects, DPOs, admins, and works councils should run it.
Copilot Studio now has three harnesses, and the new Customer Conversation harness is built for voice and chat with customers. What it means for architecture, memory, biometrics, escalation, cost, and governance.
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.
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.
A practitioner's reference for Power Platform core, Copilot Studio, Dataverse, Dynamics 365 Contact Center, and Dynamics 365 Customer Service.
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, 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.
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.
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.
An in-depth exploration of Microsoft Frontier Agents, their architecture, capabilities, and impact on enterprise AI transformation.
Master automated testing for Copilot Studio agents with the Copilot Studio Kit. Learn Phase-4 testing practices, multi-turn validation, compliance checks, and how to integrate tests into Power Platform pipelines for enterprise-grade deployments.
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.
