Notes from the trenches of real projects. What worked, what didn't, and why — no marketing spin.
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.
A practitioner's reference for Power Platform core, Copilot Studio, Dataverse, Dynamics 365 Contact Center, and Dynamics 365 Customer Service.
Where Cowork fits in Microsoft's broader agent strategy — M365 E7, Agent 365, the Researcher with Critique, and what to plan for next.
A frequent question around Microsoft Copilot Studio is: 'How does billing actually work, and where can I see what my agents consume?' The short answer is: Copilot Studio billing is usage-based and fully transparent through the built‑in Analytics experience.
The honest list of what Cowork cannot do today — by design or by current state — so you can plan rollouts without mid-pilot surprises.
Attaching files and grounding Cowork with work context — supported file types, size limits, and the patterns that improve output quality.
Cowork's control surface — per-action approvals with risk indicators, pause/resume, the Tasks view, and scheduled prompts.
Enterprise Search and Deep Research in Cowork, including the Researcher agent with Critique and its measurable quality lift on DRACO.
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.
