https://e343c64b.dataagentx.pages.dev/en/tags/microsoft-fabric/Recent content in Microsoft Fabric on DataAgentXHugoen-USSat, 26 Sep 2026 00:00:00 +0000https://e343c64b.dataagentx.pages.dev/en/products/20260926-microsoft-fabric-readonly-agent/Sat, 26 Sep 2026 00:00:00 +0000https://e343c64b.dataagentx.pages.dev/en/products/20260926-microsoft-fabric-readonly-agent/<p><a href="https://e343c64b.dataagentx.pages.dev/images/articles/microsoft-fabric-readonly-agent/core-en.svg"><img src="https://e343c64b.dataagentx.pages.dev/images/articles/microsoft-fabric-readonly-agent/core-en.svg" alt="Read-only execution gates in Microsoft Fabric Data Agent"></a></p> <p>Must an agent modify data or send tickets to be valuable? Fabric Data Agent takes a narrower position: it generates and executes read-only SQL, DAX, and KQL, leaving cross-system writes to external orchestration.</p> <h2 id="identity-comes-before-querying">Identity comes before querying</h2> <p>Data access runs under the user’s Microsoft Entra ID and source permissions. Seeing a schema does not grant permission to read its data. Power BI semantic models remain subject to Read permission, RLS, and CLS. Enforcement stays in the data platform rather than in prompt instructions.</p>https://e343c64b.dataagentx.pages.dev/en/tech/20260917-data-agent-vendor-map/Thu, 17 Sep 2026 00:00:00 +0000https://e343c64b.dataagentx.pages.dev/en/tech/20260917-data-agent-vendor-map/<p>The easiest Data Agent market map to draw incorrectly is a wall of logos that mixes cloud platforms, BI applications, internal systems, open-source frameworks, and research projects. They may serve different jobs, occupy different layers, and accept different production responsibilities.</p> <p>A useful map has two axes: system position and delivery model. Find peers first, then compare them.</p> <p><a href="https://e343c64b.dataagentx.pages.dev/images/articles/data-agent-vendor-map/core-en.svg"><img src="https://e343c64b.dataagentx.pages.dev/images/articles/data-agent-vendor-map/core-en.svg" alt="The Data Agent market layered by data platform, semantics, agent platform, analytics application, and engineering"></a></p>