Notes from real projects. What worked, what didn't, and why — no marketing spin.
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.
Custom skills replace the prompt library as the way organizations package know-how in Microsoft 365 Copilot. Here is what a skill actually is, why it beats a prompt, and why Agent Builder is enough for most of them - no Copilot Studio required.
Building long-running business processes in Copilot Studio using standard harness, state tables, agent flows, and multi-agent orchestration. Boring but effective and save
Child agents, connected agents, A2A, MCP, and the new skills: which of them exist in which harness, why, and how I decide before a single agent gets built.
The new workflows experience: Here is what the agent node does, where it belongs in a build, and the boundaries I now check before I ship one.
What I have learned running Copilot Cowork in real tenants: how to enable it (including the EU data-boundary decision), what the skills actually do, where the limits bite, and what is coming.
With agents, a single request can fan out into model calls, retrievals, retries, and tool actions that cost far more than the prompt suggests. Here's how I measure, allocate, and govern that full cost — not just the token line — and tie it to outcomes.
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.
