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.
Building production-ready conversational agents in Microsoft Copilot Studio requires mastering a critical architectural principle: the LLM handles the words, Power Fx handles the computation.
Explore how the Visual Studio Code AI Toolkit Extension Pack enables seamless development of intelligent, agentic applications from local prototyping to cloud deployment with Microsoft Foundry. This article provides a technical deep dive into model selection, agent orchestration, MCP tool integration, evaluation pipelines, and runtime tracing, complete with YAML-to-code examples in Python and C#.
High-volume inbound channels — emails, chats, and calls — drain service and sales teams when most queries are routine. A multi-agent system in Microsoft Copilot Studio can autonomously handle product lookups, quote generation, troubleshooting, and recruiting guidance, escalating only the exceptions to human reps. This article shows you how to architect, deploy, and govern specialized agents that integrate with Dynamics 365 Customer Service and Sales, cutting response times and freeing your teams for high-value work.
Explore how Microsoft Copilot Studio's multi-agent orchestration enables specialized agents to collaborate across systems using embedded agents, connected agents, and the Model Context Protocol (MCP). Learn architectural trade-offs, governance implications, and practical implementation patterns to scale your agent ecosystem effectively.
Learn how to leverage Model Context Protocol (MCP) to connect AI agents with Dynamics 365 Sales for automated lead prioritization, improving sales efficiency, and pipeline quality.
Unlock the power of specialized AI models in Microsoft Copilot Studio with a omplete Bring Your Own Model (BYOM) guide! Connect GPT-4.5, Llama, or your fine-tuned models directly into agents—no coding required. From setup to governance, learn how to build domain-specific, compliant AI solutions in just 10-15 minutes.
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.
