Microsoft Copilot – EduDataSci – Educating the world about data and leadership

One Agent, Several Kinds of Truth

An enterprise agent rarely fails because it cannot produce a fluent paragraph. It fails because it cannot distinguish the current balance from the definition of balance, the approved policy from the email that discussed an exception, or the authority to explain a decision from the authority to change a system of record.

That distinction matters in financial services. A relationship manager asking why a commercial borrower has become riskier is really asking several questions at once. What changed in the borrower’s accounts? How does the exposure roll through facilities, collateral, guarantees, and legal entities? What does credit policy require? What did the deal team agree to last week? If action is warranted, who may open a review, request documents, or change a limit?

No single knowledge source can answer all of that honestly. The useful architecture is a Copilot Studio agent that coordinates several bounded kinds of intelligence: Fabric IQ for business state, Foundry IQ for institutional knowledge, Work IQ for the user’s working context, an ontology for shared meaning, and MCP tools for controlled action. API Center anchors design-time inventory and discovery, while Microsoft Purview anchors data governance and supported AI-interaction compliance. Runtime enforcement remains with Entra, Power Platform data policies, native IQ permissions, API Management, and the source systems.

Power BI Copilot Has Multiple Modes. Here’s What Each One Does—and How Fabric Data Agents Change the Game.

Copilot in Power BI isn’t “one feature.” It’s a growing set of experiences that show up in different places, behave differently, and—most importantly—solve different problems.

That’s why two people can both say “Copilot didn’t work for me,” and both be right. One might be trying to generate a report page in Desktop. Another might be trying to chat across any model in their tenant. A third might be expecting an agent-like experience that stays grounded in a curated subject area.

In this post, we’ll map the major modes of Power BI Copilot (where it shows up, what it’s best at, and what it’s not), then contrast that with Fabric Data Agents—because Data Agents aren’t a “better Copilot.” They’re a different building block, meant for a different kind of outcome.

Ignite 2025 Beyond the Data Platform: How Microsoft Is Turning Everything Into an Agent Platform

Microsoft Ignite 2025 is officially the “Frontier firm” show—agents everywhere, all at once. If you’ve been tracking the data platform news (Fabric, databases, OneLake), you already know that story. This post looks at the rest of the landscape: Windows, Microsoft 365, Teams, Edge, security, Azure infra, and the growing partner ecosystem that’s rapidly filling in the agent-shaped gaps.

I’ll walk through the major non‑data platform announcements and highlight where Microsoft and partners are quietly reshaping the application, OS, and security layers around #Copilot, #AgenticAI, and #MSIgnite. Then we’ll close with what this means for architects and teams trying to build something coherent on top of all of this.

Microsoft Ignite – Wrap Up and Data Platform News

It’s always hard to sit down and fully absorb the information you get at a conference like Microsoft Ignite. You spend a week living in and around the tech world, just trying to drink in everything and interact with as many people as possible. I’m still doing more than a little digesting about what all of these announcements last week have meant, but I’m excited about quite a few of them, especially on the data platform side.