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.
Learn how to connect the Outlook Model Context Protocol (MCP) server with Microsoft Copilot Studio agents to enable intelligent, email-driven automation workflows without writing code. This article covers configuration steps, available email operations, and a complete example of an autonomous agent handling order status inquiries.
Technical overview and configuration guide for additional Microsoft first‑party autonomous agents for Dynamics 365 Sales and Service, including purpose, scope, expected outcomes, prerequisites, enablement steps, key configuration choices, and guardrails.
Technical overview and configuration guide for Microsoft first‑party autonomous agents for Dynamics 365 Customer Service, Contact Center, and Sales, including purpose, scope, expected outcomes, prerequisites, enablement steps, key configuration choices, and guardrails.
Practical strategies for IT and business managers to implement effective governance frameworks that balance innovation with security in Microsoft Copilot Studio and the Power Platform.
This article explores how to integrate SAP systems with Microsoft Copilot Studio Agents, enabling AI-driven interactions and workflows within enterprise environments. It covers architecture, use cases, and best practices for leveraging SAP data in AI agents.
Microsoft has open‑sourced Agent Framework, a unified SDK and runtime for building, orchestrating, and operating multi‑agent AI systems across Python and .NET, with open standards (MCP, A2A, OpenAPI), graph‑based workflows, observability via OpenTelemetry, and enterprise‑grade durability and governance. It consolidates the strengths of Semantic Kernel and AutoGen, enabling teams to prototype locally and then ship to Azure AI Foundry Agent Service, where agents are surfaced across Microsoft 365 endpoints—without the need to rewrite code.
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.
