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.
Microsoft Copilot Studio's new deep reasoning models significantly advance AI agent capabilities, enabling complex problem-solving, logical analysis, and multi-step decision-making. This feature empowers organizations to build virtual agents that can analyze unstructured data, make contextual recommendations, and support sophisticated business processes—all while maintaining accuracy and thoughtful analysis. Learn how deep reasoning models are transforming AI agents from simple Q&A tools into powerful decision-support systems for business intelligence, operations, education, and customer support.
Learn how to build conversational AI applications using Microsoft Fabric Data Agents and Azure AI Agents.
Agent flows are a powerful way to automate repetitive tasks and integrate your apps and services. These intelligent automation workflows can be triggered manually, by other automated events or agents, or based on a schedule, providing flexible options for process automation. By leveraging agent flows, organizations can streamline operations, reduce manual intervention, and ensure consistent execution of business processes.
This article explores the implementation of a pay-as-you-go (PAYG) payment model for Copilot Studio agents and agent flows, highlighting its economic advantages, practical setup guidance, and monitoring strategies. By adopting the PAYG model, organizations can optimize resource allocation, reduce upfront costs, and maintain operational continuity while leveraging advanced AI capabilities.
Learn how to integrate AI Builder prompts into Microsoft Copilot Studio agents to enhance workflows and productivity.
The Model Context Protocol (MCP) is an open protocol designed to standardize how applications provide context to large language models (LLMs). It enables seamless connections to data sources and tools through a client-server architecture, offering features like pre-built integrations, flexibility, security, extensibility, and interoperability.
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.
