Notes from the trenches of real projects. What worked, what didn't, and why — no marketing spin.
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.
A practitioner's reference for Power Platform core, Copilot Studio, Dataverse, Dynamics 365 Contact Center, and Dynamics 365 Customer Service.
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.
A practitioner's reference for Power Platform core, Copilot Studio, Dataverse, Dynamics 365 Contact Center, and Dynamics 365 Customer Service.
Microsoft MVP & MCT | Low Code Hacker | Copilot, Copilot Studio, Power Platform & Azure Architect
I’m a Microsoft MVP focused on agentic AI, intelligent agents, and enterprise AI solutions. Using Microsoft Copilot Studio and Azure AI Foundry, I design and build systems that help people and organizations work smarter. This blog is a collection of field notes, practical insights, and real-world experiences—from architecture and orchestration patterns to lessons learned along the way. Your feedback is always welcome—let’s continue the conversation.
