Care and Lowcode

Why being ready to build isn’t the same as being ready to deploy In my last post, the signal was clear, we’ve moved past hesitation. People are building in Copilot Studio, experimenting, and focusing on personal improvement, developing skills, learning by doing, and starting to see real value. And that’s exactly where many of us are right now: we’ve invested the time, built some agents, and started to see what’s possible. That’s the good part. The gap? Deployment. Because deploying Microsoft 365 agents isn’t a feature toggle - it’s a shift in how you operate. When I went through Microsoft’s official checklist, it reinforced something important: most of the complexity isn’t in building agents - it’s in running them safely, consistently, and at scale. Source: Microsoft Step 1. Successful deployment starts with people Deployment is not a solo effort. It requires cross‑functional orchestration: Copilot Administrator – owns Copilot Control System (CCS) and agent lifecycle. Microsoft 365 A...

A practical walkthrough of building a Copilot Studio agent connected to the Microsoft Learn MCP server - what worked, what confused me, and what I would do differently. If you have been putting off studying for AB-730 -AI Business professional , this might change that. I built a dedicated study tutoring agent in Copilot Studio, connected it to the Microsoft Learn MCP server, and used it to prepare for the AI Business Professional exam. Here is exactly what I built and what I wish I had known earlier. Why I built it this way and what is MCP? The AB-730 exam tests precision, not broad knowledge. It focuses on specific details about how Copilot works across Microsoft 365, Responsible AI guardrails, and governance boundaries. A general AI chat tool drifts. It gives answers that sound right but are not grounded in the actual Microsoft documentation. I needed something that stayed on source. That is what MCP makes possible. Model Context Protocol (MCP) allows users to connect with existing ...

Now that most organizations have access to Microsoft 365 Copilot Chat, something interesting is happening: you can build simple AI agents without coding, Copilot Studio, or expensive tools. But in healthcare and public services, the challenge isn’t building agents. It’s building trust. After 10 years on the frontline supporting children and families, I know how quickly tools fail when they don’t fit reality: • Staff are busy • Documentation is heavy • Risk of sharing sensitive information is constant So I built MICO,  and in this post I'll walk through exactly how it works, what design decisions I made, and why the governance layer matters more than the features. Who Is MICO? MICO (Miljøarbeidtjenesten's Copilot Opplæringsagent), an agent built in Agent Builder using Microsoft 365 Copilot Lite versions, grounded in Microsoft’s best practices, the kommunes guardrails, GDPR compliance, Responsible AI principles, and real-world healthcare scenarios. Not a chatbot, but a Copilot co...

Last week at Microsoft AI Tour Oslo , governance was presented as a core component of enterprise AI deployment within Microsoft 365. Microsoft referenced the Copilot Control System as the structured framework for managing, securing, and measuring AI capabilities across: Microsoft 365 Copilot Copilot Chat Microsoft 365 prebuilt agents Custom agents built in Microsoft Copilot Studio Microsoft structures the Copilot Control System around 3 pillars: Security and governance Management controls Measurement and reporting This structure integrates with existing Microsoft 365 administrative and compliance tooling rather than introducing a separate AI governance system. Image source: Copilot Control System Security and Governance Copilot operates within existing Microsoft 365 security boundaries. It inherits: User permissions Sensitivity labels configured in Microsoft Purview Compliance features such as audit logging and retention policies AI functionality does not...