#semanticmodel

Jun 4, 2025

Automatically populate Data Agents with Semantic Model Synonyms

Automatically populate Data Agents with Semantic Model Synonyms, however note that synonyms are used by data agents. Excellent blog none the less on getting the data AI ready.

Jan 28, 2026

Microsoft Fabric Copilot: Building a Foundation of Trust Before You Ask Questions!

The blog discusses why establishing a strong foundation of trust is essential before users begin asking questions to Microsoft Fabric Copilot. It emphasizes that Copilot’s effectiveness depends heavily on the quality, clarity, and governance of the underlying data and semantic models. The author explains how organizations should prepare their Fabric environment—through well‑modeled data, proper documentation, security, and metadata—so Copilot can generate accurate, reliable, and context‑aware responses. Overall, it’s a call to treat Copilot not as magic, but as a powerful layer built on top of disciplined data practices.

Hands On : Build a Direct Lake Model with Data Agents with 275M+ Healthcare Records

This solution demonstrates the capabilities of Microsoft Fabric using over 275 million rows of real-world healthcare data. It showcases how to leverage the Power BI Direct Lake connector to query large datasets stored in Delta Parquet format—without caching or a relational database. Fabric Data Agents have also been added for the Semantic Model and the Lakeouse or Warehouse. The Semantic Model is also optimized for Power BI Copilot, including the standalone version that functions as a SaaS MCP server for chatting on all of your content and data. The dataset used is the publicly available Medicare Part D Prescribers - by Provider and Drug, sourced from the Centers for Medicare & Medicaid Services (CMS). 🎥 Watch the full demo: YouTube Video https://youtu.be/2tLIGVZ4c8E

Feb 1, 2026

Fabric Data Agent for Semantic Model

This video reviews the new Semantic Model Fabric Data Agent that as been added to our free GitHub training repo with 275 million rows of real data. The new Semantic Model Data Agent can be added with a few simple steps, and then you can compare and contrast the Lakehouse and Semantic Model Data Agents.

Data Agent Client - Teams App

A Microsoft Teams application that enables natural language queries to Fabric Data Agents, featuring real-time streaming responses, DAX query visualization, and multi-agent support. - Natural Language Queries: Ask questions in plain language and get AI-powered answers from your semantic models - Multi-Agent Support: Connect to multiple Fabric Data Agents and switch between them seamlessly - Real-Time Streaming: See responses as they're generated with live progress indicators - Query Transparency: View the generated DAX code and query results for each analysis step - Teams Integration: Native Teams app experience with SSO authentication - Fluent UI Design: Modern, responsive interface following Microsoft design guidelines

Semantic Model Data Agent Readiness Analyzer

What it does: Automates 18+ critical checks to validate your Power BI semantic model is ready for Microsoft Fabric Data Agents — saves hours of manual validation Prevents production failures by detecting issues like missing descriptions, duplicate column names, implicit measures, and poor DAX performance before deployment Provides actionable scoring with severity-weighted prioritization (🔴 Critical → 🟡 Recommended) so you know exactly what to fix first Aligned with official Microsoft guidance — covers 100% of the Fabric Data Agent Checklist including security requirements, AI Data Schema validation, and performance optimization Version-controlled best practices — guides you on Prep for AI configuration (Verified Answers, AI Instructions, synonyms) that travels with your PBIP model through Git and deployment pipelines Bottom line: Run this notebook before deploying your Data Agent to catch configuration gaps that would otherwise cause silent failures, poor accuracy, or timeout errors in production.

Mar 26, 2026

What We Learned Building a Real-World Fabric Data Agent — The Honest Field Notes

The post is a detailed, field‑tested account of building a real‑world Fabric Data Agent on top of a complex industrial supply‑chain dataset, highlighting what works, what breaks, and what requires deliberate engineering. It walks through six major lessons: why agent instructions—not data sources—determine answer quality; how Semantic Models and Ontologies complement each other; the pitfalls of asynchronous graph rebuilds; the importance of using binding property names in GQL; common GQL query‑generation failures; and the hidden requirement to use dbo. prefixes in SQL. Despite the rough edges of a preview product, the author argues that Fabric IQ’s architecture—unifying SQL, DAX, and GQL behind a governed semantic layer—is powerful and worth understanding deeply for anyone building enterprise‑grade AI analytics.