# Fabric Data Agent - Full Site Content > Complete content from fabricdataagent.com - a community-driven resource hub for Microsoft Fabric Data Agents. This file contains all content from the Fabric Data Agent community site in a format optimized for LLM consumption. For a concise summary, see [llms.txt](https://fabricdataagent.com/llms.txt). Total content: 44 articles, 32 videos, 13 resources, 10 events, 9 tools, 18 LinkedIn posts, 3 learning paths. --- ## Articles ### A Data Agent Should Be a Sub-Agent - URL: https://promptingbi.com/2026/09/23/a-data-agent-should-be-a-sub-agent/ - Author: Tommy Puglia - Published: 2026-09-03 - Summary: Here’s how most data agents get built. Someone connects one to a semantic model, opens the big chat pane in the middle of the screen, and types “how are sales?” A number comes back. Everyone nods. Nobody opens it again. That’s what most people think a data agent is for: another chat interface. One more box to type into, sitting next to Copilot, ChatGPT, Claude, and whatever your company bought last quarter. I think a data agent should be a sub-agent. It’s a narrow specialist with one job written into its instructions, and a bigger agent calls it when a question needs it. People talk to Copilot, inside the tools they already work in. Copilot calls the data agent. Once you look at it that way, two things change. You stop building one data agent per semantic model, and you start writing instructions per purpose. - Tags: data-agent, multi-agent, sub-agent, foundry - Contributor: Sandeep Pawar ### Analyzing Microsoft Fabric's Data Agent - URL: https://medium.com/uselessai-in/analyzing-microsoft-fabrics-data-agent-c0ca81f62ff3 - Author: Shresth Shukla - Published: 2026-01-13 - Summary: This article analyzes data agents on a variety of tasks and queries and performs some prompt engineering to find out the change in responses. - Tags: agent-analysis, data-agent, prompt-engineering - Contributor: Shresth Shukla ### Automatically populate Data Agents with Semantic Model Synonyms - URL: https://data-marc.com/2025/06/04/automatically-populate-data-agents-with-semantic-model-synonyms/ - Author: Marc Lelijveld - Published: 2025-06-04 - Summary: 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. - Tags: semanticmodel, dataagent, prepforai, synonym - Contributor: Sandeep Pawar ### Beyond the Star Schema: Why Ontologies are the New Requirement for AI-Ready Data - URL: https://www.linkedin.com/pulse/beyond-star-schema-why-ontologies-new-requirement-ai-ready-tony-smith-yp37e - Author: Tony Smith - Published: 2026-02-19 - Summary: Relational data models weren’t designed for AI or natural language, so while they store data well, they fail to capture business meaning—making accurate, trustworthy AI querying difficult. Fabric IQ addresses this by introducing an ontology layer that sits above existing data, explicitly modelling business concepts, relationships, and rules without requiring data to be moved or reshaped. Combined with Fabric Data Agents, this enables AI to navigate defined meaning rather than guess it, improving query accuracy, consistency, and scalability for enterprise analytics. - Tags: fabric, fabriciq, dataagents, ontology, aianalytics - Contributor: Tony Smith ### Bringing Power BI Insights to Every Copilot User - URL: https://community.fabric.microsoft.com/blog/fbc_pbiupdatesblog/bringing-power-bi-insights-to-every-copilot-user/5309360 - Author: Sara Vredevoogd - Published: 2026-07-20 - Summary: Power BI helps people understand their data and act on it. With AI, what’s changing is where trusted analytics can meet users: in the flow of work, at the moment a decision is being made, without forcing them to hunt for the right report first. As AI becomes part of everyday work, it’s critical to bring trusted Power BI data to where work gets done. We’re in a phase of AI where systems can answer questions and help complete tasks for a user. But for business data, that only works when AI can reason over governed definitions instead of guessing from raw tables. That’s why we’ve invested in ensuring your Power BI data shows up everywhere you already work, starting with Microsoft 365 Copilot. And it works because of the thing your team has invested in for years: a well-modeled semantic layer. - Tags: powerbi, powerbi-insights, powerbi-copilot - Contributor: Parv Chana ### Blog: What’s new in Neo4j Graph Intelligence for Microsoft Fabric - shows how to use exported results with Fabric Data Agents - URL: https://neo4j.com/blog/developer/whats-new-neo4j-graph-intelligence-microsoft-fabric/ - Author: Stu Moore - Published: 2026-05-15 - Summary: Graph Intelligence for Fabric can now Export results to Lakehouse to answer complex data questions in Copilot using Fabric Data Agents  — Whether you run PageRank or Betweenness to find influential products, the most likely bottlenecks in supply chains, or detect fraudulent communities with Louvain, these graph-based insights can be replicated back to the source tables or create fresh result tables. - Tags: data-agent, graphalgorithms, graphdatabases - Contributor: Stu Moore ### Building a Fabric Data Agent with On‑Premises SQL Server Data - URL: https://www.linkedin.com/pulse/building-fabric-data-agent-onpremises-sql-server-pablo-junco-boquer-1xv8e/?trackingId=vLGBvPezTfOuuLx0FYkj1g%3D%3D - Author: Pablo Junco Boquer - Published: 2026-04-27 - Summary: Many organizations still rely on on‑premises SQL Server for core operational workloads — finance, billing, ERP, manufacturing, and regulatory systems — that cannot be easily migrated to the cloud. At the same time, the business is demanding: Conversational access to data (“Ask the data” experiences) AI‑powered insights without building fragile ETL pipelines Faster time‑to‑value from analytics and AI Strong governance, security boundaries, and system ownership Microsoft Fabric addresses this challenge by allowing organizations to bring AI to their data before moving their data to AI. By leveraging SQL Server mirroring into Microsoft Fabric, organizations can continuously replicate on-premises data into OneLake, making it immediately available for analytics and AI—without disrupting source systems. On top of this foundation, semantic models and Fabric Data Agents enable governed, natural-language interactions powered by Microsoft Copilot. - Tags: data-agent, sql, on-prem, fabric - Contributor: Sandeep Pawar ### Building a Spider2-Inspired Benchmark to Measure the Real Robustness of a Fabric Data Agent in Italian - URL: https://lucazavarella.medium.com/building-a-spider2-inspired-benchmark-to-measure-the-real-robustness-of-a-fabric-data-agent-in-ita-abe6f0781b34 - Author: Luca Zavarella - Published: 2026-03-14 - Summary: This article moves from working demos to measurable reliability by introducing a Spider2-inspired benchmark for evaluating a Fabric Data Agent in Italian. It explains why manual spot checks are not enough, and shows how to design a more rigorous evaluation framework that separates already-taught patterns from true generalization. The result is a practical benchmark design for assessing multilingual Fabric Data Agents beyond isolated successful examples. - Tags: data-agent, fabric, multilingual - Contributor: Luca Zavarella ### Can One Fabric Data Agent Replace 10 Power BI Reports? A Migration Playbook - URL: https://medium.com/@malharpawar/can-one-fabric-data-agent-replace-10-power-bi-reports-a-migration-playbook-785a6de0fec2?postPublishedType=initial - Author: Malhar Pawar - Published: 2026-10-06 - Summary: Most Power BI migrations to Fabric Data Agents fail not because of the agent but because of the semantic model underneath it. This playbook covers how to audit your report estate, classify what to migrate vs. retire vs. keep, score your semantic model for AI readiness, and run a structured 12-week migration with ground-truth validation and RLS testing. - Tags: data-agent, fabric, power-bi, semantic-model, migration, governance, prep-for-ai, enterprise-bi, analytics-engineering - Contributor: Malhar Pawar ### Can You Trust Your Fabric Data Agent? Programmatically Testing Accuracy and Determinism - URL: https://data-marc.com/2026/10/27/can-you-trust-your-fabric-data-agent-programmatically-testing-accuracy-and-determinism/ - Author: Marc Lelijveld - Published: 2626-10-27 - Summary: Blog on how to set up data agent evaluation using Python SDK - Tags: dataagent, evaluation, pythonsdk, accuracy - Contributor: Sandeep Pawar ### Chat with your data using Microsoft Fabric data agents - URL: https://microsoftlearning.github.io/mslearn-fabric/Instructions/Labs/22d-copilot-fabric-data-agents.html - Author: Microsoft Learn - Published: 2026-01-01 - Summary: Chat with your data using Microsoft Fabric data agents A Microsoft Fabric data agent enables natural interaction with your data by allowing you to ask questions in plain English and receive structured, human-readable responses. By eliminating the need to understand query languages like SQL (Structured Query Language), DAX (Data Analysis Expressions), or KQL (Kusto Query Language), the data agent makes data insights accessible across the organization, regardless of technical skill level. - Tags: data-agent, mslearn, microsoftlearn, fabric, data-agentexercise, data-agenttutorial - Contributor: Parv Chana ### Creating Data Agent in Microsoft Fabric — First Impression - URL: https://uselessai.in/creating-data-agent-in-microsoft-fabric-first-impression-78a2039a52e2 - Author: Shresth Shukla - Published: 2026-01-09 - Summary: To give you a bit of background on what this data agent is all about, think of it as your assistant that knows everything about your data. Just like you use ChatGPT, you can leverage LLM capabilities on your enterprise data and have conversations over your database. - Tags: data-agent, fabricdataagent, microsoftfabric - Contributor: Parv Chana ### Creating Data Agent in Microsoft Fabric - First Impression - URL: https://medium.com/uselessai-in/creating-data-agent-in-microsoft-fabric-first-impression-78a2039a52e2?source=your_stories_outbox---writer_outbox_published----------------------------------------- - Author: Shresth Shukla - Published: 2026-01-12 - Summary: The article walks us through the creation of data agent for first time user and explores various ways to play around data agent. - Tags: data-agent, fabric - Contributor: Shresth Shukla ### Creating Microsoft Fabric Data Agent using python sdk programmatically - URL: https://medium.com/uselessai-in/creating-microsoft-fabric-data-agent-using-python-sdk-programmatically-15af4340bee8 - Author: Shresth Shukla - Published: 2026-01-19 - Summary: This article explores creation of Data Agent programatically using Python SDK for data agents. - Tags: data-agent, python-sdk, dataagentusingpython - Contributor: Shresth Shukla ### Best Practices for Fabric Data Agent Development - URL: https://blog.fabric.microsoft.com/data-agent-best-practices - Author: Fabric Blog - Published: 2026-01-10 - Summary: A collection of best practices and design patterns for building production-ready data agents in Microsoft Fabric, including error handling, performance optimization, and security considerations. - Tags: best-practices, production, architecture - Contributor: Sandeep Pawar ### Data Agent in Microsoft Fabric – Here’s How it Works by Azure Ops - URL: https://azureops.org/articles/data-agent-in-microsoft-fabric-heres-how-it-works/ - Author: AruzeOps.Org - Published: 2026-01-01 - Summary: **Data Agent in Microsoft Fabric – Here’s How it Works** Ever wished you could just ask your data questions in plain English and get instant, intelligent answers? With Microsoft Fabric’s new Data Agent, that’s not just possible, it’s powerful. In this post, I’ll walk you through how I built a Fabric Data Agent on top of the standard AdventureWorksDW dataset, and how you can too, even if you’re a complete beginner. - Tags: data-agent, fabric, learndata-agent, howdataagentworks - Contributor: Parv Chana ### Data Agent Now Supports Eventhouse Functions, Materialized Views, and Shortcuts (Preview) - URL: https://community.fabric.microsoft.com/t5/Fabric-Updates-Blog/Data-Agent-Now-Supports-Eventhouse-Functions-Materialized-Views/ba-p/5181801 - Author: Shreyas Canchi Radhakrishna - Product Manager @ MSFT - Published: 2026-05-13 - Summary: New capabilities in Fabric Data Agent are now available to expand what's possible when data agent is integrated with Eventhouse KQL Databases. Data Agent now supports Eventhouse User Defined Functions (UDFs), Materialized Views (MV), and Shortcut tables enabling your AI-powered agent access to the full breadth of your Eventhouse KQL database. - Tags: data-agent, fabric, gettingstarted, newfeature - Contributor: Parv Chana ### Designing AI‑Ready Analytics with Microsoft Fabric Data Agents - URL: https://www.linkedin.com/pulse/designing-aiready-analytics-microsoft-fabric-data-pablo-junco-boquer-gjnwe/?trackingId=80CulpGNR9K%2FNNi1mwFr9g%3D%3D - Author: Pablo Junco Boquer - Published: 2026-04-01 - Summary: s organizations accelerate their adoption of AI-powered analytics, a new challenge is emerging: how to expose trusted business data to AI—Copilot, data agents, and conversational analytics—in a way that is secure, cost-predictable, and architecturally sound. Most enterprises are already operating in a complex reality: Power BI reports connected to operational systems like Oracle, SAP, and SQL Server A mix of Import and DirectQuery semantic models Strong governance expectations around security, lineage, and cost control - Tags: data-agent, capacity, planning - Contributor: Sandeep Pawar ### E-commerce ontology and data agent in Microsoft Fabric IQ - URL: https://ravichanduedru.me/articles/fabric-iq/build-ecommerce-ontology-fabric-iq - Author: Ravi Chandu Edru - Published: 2026-07-23 - Summary: Your data can be clean, complete, and connected, and still fail to answer a simple business question. Microsoft Fabric IQ solves this with something called an ontology. I built one end to end, connected a data agent to it, and wrote down every step. If you have never touched an ontology before, this guide is for you. Without an ontology, an AI agent can only guess at your data. - Tags: data-agent-, fabric-iq, ontology, ecommerce, tutorial, hands-on, ai, analytics - Contributor: Sandeep Pawar ### Fabric Data Agent vs Copilot in Power BI - URL: https://www.linkedin.com/pulse/fabric-data-agent-vs-copilot-power-bi-leon-gordon-b6ece/ - Author: Leon Gordon - Published: 2026-08-16 - Summary: I get asked the same question in almost every Fabric estate review I run. Do we put Copilot on the semantic model, or point a data agent at the warehouse? It nearly always arrives as an intelligence contest, which one is smarter. That is the wrong question. In a Fabric estate where both ultimately work from the same governed gold data, the important difference is not the underlying data. It is how much semantic context sits between the question and that data, and the surface whose grounding matches the shape of the question is the one that answers accurately. The decision is architectural, not a bake-off. You have a clean setup: star schemas in gold, semantic models on top, reports that people trust. Now the business wants to type a question and get an answer. The reporting side says put Copilot on the semantic model. The warehouse side says point a data agent at the warehouse. Both are correct, for different questions and the failure mode is choosing on vibes. - Tags: data-agent, powerbi-semantic-model - Contributor: Parv Chana ### Fabric Data Agents in Microsoft Copilot Studio - URL: https://community.fabric.microsoft.com/blog/fbc_fabricupdatesblogs/fabric-data-agents-in-microsoft-copilot-studio-generally-available/5362882 - Author: Amir Jafri - Published: 2026-09-02 - Summary: Organizations can now bring governed business data from Microsoft Fabric into Copilot Studio agents, enabling agents to answer questions, generate insights, and support business processes using trusted enterprise data. Fabric data agents make it easier to ground experiences in the data your organization already relies on. Since we announced this integration in preview, both Fabric and Copilot Studio have evolved significantly. General availability provides a more integrated experience, broader publishing options, and a stronger foundation for deploying data-powered agents across the Microsoft ecosystem. - Tags: data-agent, m365copilot, fabric - Contributor: Parv Chana ### Fabric Data Agents: The Shift from Querying Data to Reasoning Over Knowledge - URL: https://community.fabric.microsoft.com/t5/IQ-Community-Blog/Fabric-Data-Agents-The-Shift-from-Querying-Data-to-Reasoning/ba-p/5139442 - Author: Jennifer Ratten - Published: 2026-03-26 - Summary: **What’s the big deal?** Fabric is no longer just a data platform. It’s becoming a system that can reason over enterprise knowledge. The real shift is the move from human-authored to AI-authored logic, under guardrails. **Before** Humans write explicit queries, design semantic models, orchestrate pipelines. Tools act as passive executors, doing exactly what they are told. **Now** Humans declare the intent. Agents determine the plan (how to answer) and execute across governed data, semantic and orchestration layers. - Tags: data-agent, whatisdataagent, fabric - Contributor: Parv Chana ### Ground Truth Before Go-Live: Building Better Fabric Data Agents with Automated Evaluation Datasets - URL: https://community.fabric.microsoft.com/t5/Data-Science-Community-Blog/Ground-Truth-Before-Go-Live-Building-Better-Fabric-Data-Agents/ba-p/5303092 - Author: Jennifer Ratten - Published: 2026-07-20 - Summary: One of the biggest challenges when building a Fabric data agent isn't creating the agent itself, it's knowing whether the answers it provides are consistently accurate. Many teams test a new agent by manually asking a handful of questions and reviewing the responses. While this approach can uncover obvious issues, it doesn't scale and it doesn't provide a reliable way to measure improvements over time. That's where ground truth datasets come in. A ground truth dataset is a collection of questions paired with known-correct answers derived directly from your semantic model. These datasets become the benchmark against which your Fabric data agent can be evaluated. - Tags: data-agent, evaluation, pythonsdk, groundtruth - Contributor: Sandeep Pawar ### How to connect a Fabric Data Agent to Microsoft Copilot Studio as a connected agent - URL: https://www.linkedin.com/pulse/how-connect-fabric-data-agent-microsoft-copilot-manoj-annavajjala-viwlc/ - Author: Manoj Annavajjala - Published: 2026-07-20 - Summary: Most Copilot Studio agents are excellent at answering questions from documents and websites, but weak at answering questions that require live, governed access to organizational data. Microsoft Fabric closes that gap with data agents: configurable, read-only conversational layers over lakehouses, warehouses, Power BI semantic models, and KQL databases. Connecting a Fabric data agent into Copilot Studio as a connected agent lets a custom Copilot Studio agent hand off data questions to Fabric while keeping the conversation, orchestration, and channel deployment in Copilot Studio. This article walks through what a Fabric data agent actually does, how the Copilot Studio connection works step by step, what governance changes the moment data leaves Fabric's compliance boundary, and a grounded estimate of what the whole setup costs to run at enterprise scale. - Tags: data-agent, mcs, copilot-studio, fcc, agent, billing - Contributor: Sandeep Pawar ### Implementing Data Agent in Microsoft Fabric for comprehensive business insights - URL: https://www.bakertilly.com/insights/implementing-data-agent-in-microsoft-fabric-for-comprehensive-business-insights - Author: Chris Wagner - Published: 2025-03-31 - Summary: **Leveraging the semantic model for business insights** The semantic model in Microsoft Fabric plays a crucial role in transforming raw data into meaningful business insights. By accessing the semantic model, Data Agent can understand and interpret complex data relationships, providing a unified view of the data that aligns perfectly with current reporting and analytical needs. - Tags: data-agent, fabric, data-agenttutorial - Contributor: Parv Chana ### Microsoft Fabric Copilot: Building a Foundation of Trust Before You Ask Questions! - URL: https://data-marc.com/2026/01/28/microsoft-fabric-copilot-building-a-foundation-of-trust-before-you-ask-questions/ - Author: Marc Lelijveld - Published: 2026-01-28 - Summary: 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. - Tags: copilot, governance, prepforai, semanticmodel - Contributor: Sandeep Pawar ### Microsoft Fabric Data Agent — Complete Guide by Alpa Buddhabhatti - URL: https://medium.com/@meetalpa/microsoft-fabric-data-agent-complete-guide-e6c157fd4a48 - Author: alpa buddhabhatti - Published: 2025-08-12 - Summary: Unlock natural language access to your enterprise data with Microsoft Fabric Data Agent. - Tags: data-agent, dataagent, fabricdataagent - Contributor: Parv Chana ### Microsoft Fabric Data Agents: Bringing Structured and Unstructured Data Together - URL: https://www.jamesserra.com/archive/2026/09/microsoft-fabric-data-agents-bringing-structured-and-unstructured-data-together/ - Author: James Serra - Published: 2023-09-01 - Summary: Most enterprise questions do not live neatly in one place. The numbers may be in a warehouse, the rules may be buried in PDF files, and the explanation may sit in a support document that only three people know exists. A [Microsoft Fabric data agent](https://learn.microsoft.com/en-us/fabric/data-science/concept-data-agent?utm_source=chatgpt.com) gives users a conversational way to ask questions across that information while keeping the answer grounded in approved enterprise data. I think of it as a configurable virtual analyst for a business domain, not a generic chatbot that happens to know a little SQL. Fabric Data Agents are now generally available, while some of the newer data sources, integrations, and advanced capabilities discussed later in this post are still in preview. - Tags: data-agent, unstructureddata, aisearch - Contributor: Sandeep Pawar ### New article: Which Verdicts Changed, and Why: a Row-Level Audit of Fabric Data Agent Evaluation - URL: https://medium.com/data-science-collective/which-verdicts-changed-and-why-a-row-level-audit-of-fabric-data-agent-evaluation-01b0f1969a71 - Author: Luca Zavarella - Published: 2026-04-07 - Summary: The author performs a detailed row‑level audit of a 72‑question benchmark to understand why evaluation verdicts changed after fixing errors in the benchmark itself. Many initial “failures” turn out to be caused by faulty ground truth, ambiguous phrasing, or inconsistent casing rules rather than true Data Agent mistakes. After refining benchmark wording, tightening Agent instructions, and clarifying metric definitions, accuracy rises to 97.2%. The few remaining errors stem from extremely complex multi‑step prompts and ambiguous schema references, revealing limits of the underlying model rather than flaws in the benchmark. - Tags: data-agent, fabric, evaluation - Contributor: Luca Zavarella ### Fabric Data Agents Are English-First (For Now): A Hands-On Guide to Configuring One on Zava DIY for Non-English Users - URL: https://medium.com/data-science-collective/fabric-data-agents-are-english-first-for-now-a-hands-on-guide-to-config-one-for-non-english-users-cb16e31c4bd1 - Author: Luca Zavarella - Published: 2026-03-04 - Summary: This article provides a hands-on, incremental guide to configuring a Microsoft Fabric Data Agent on the Zava DIY dataset for non-English users, while keeping the agent grounded in an English-first setup. It shows how to improve reliability step by step through data source descriptions, agent instructions, domain constraints, formatting rules, and validated example queries, then extends the configuration with a practical "translate in, translate out" approach. The result is a reproducible quick-win pattern for making the agent more analytics-ready across languages without introducing external translation layers or custom front ends. - Tags: fabric, data-agent, multilingual - Contributor: Luca Zavarella ### Ontologies: What Do I Mean vs What Do I Want? - URL: https://www.linkedin.com/pulse/ontologies-what-do-i-mean-vs-want-tony-smith-cuage - Author: Tony Smith - Published: 2026-03-26 - Summary: The article argues that prompt‑heavy approaches to natural language querying are fundamentally brittle because they force LLMs to manage meaning, preference, and logic simultaneously—something they are not designed to do, leading to ambiguity and inconsistency in enterprise analytics. It positions Fabric Data Agents as a more structured alternative, where instructions are deliberately scoped to behaviour and intent, while meaning is externalised—reducing the fragility seen in traditional prompt stacks. Fabric IQ is presented as the key enabler of this shift, providing ontologies as a first‑class semantic layer that lets agents move from inferring business meaning to reliably navigating explicit definitions, making natural language over enterprise data more consistent and scalable. - Tags: fabriciq, fabricdataagents, ontology, llms - Contributor: Tony Smith ### Programmatically Retrieve Prep Data For AI Configuration of Semantic Models - URL: https://fabric.guru/programmatically-retrieve-prep-data-for-ai-configuration-of-semantic-models - Author: Sandeep Pawar - Published: 2026-04-02 - Summary: For Power BI Copilot and [Data agents with semantic models](https://learn.microsoft.com/en-us/fabric/data-science/semantic-model-best-practices#prep-for-ai-make-semantic-model-ai-ready), you must use [Prep Data for AI configuration](https://learn.microsoft.com/en-us/power-bi/create-reports/copilot-prepare-data-ai) to ground the responses in the context added in Prep for AI. In this blog, I will show you how you can use the [Power BI remote MCP server](https://learn.microsoft.com/en-us/power-bi/developer/mcp/remote-mcp-server-get-started) to get the configuration. - Tags: data-agent, mcpserver, powerbi, microsoftfabric, dataagenteverything - Contributor: Parv Chana ### Semantic layers: giving AI agents business context - URL: https://maciejkepa.dev/blog/semantic-layers-ai-agents/ - Author: Maciej Kępa - Published: 2026-11-05 - Summary: A semantic layer is not merely metadata; it is the mechanism that gives AI agents a shared, governed understanding of business metrics so they can answer analytical questions consistently, correctly, and securely - Tags: data-agent, semantic-layer, context - Contributor: Sandeep Pawar ### Take your data agents to production with BI Pixie - URL: https://bipixie.com/blog/introducing-ai-readiness - Author: Gil Raviv - Published: 2026-08-25 - Summary: For two years BI Pixie has measured how people use your Power BI: who adopts a report and who stops coming, what they click, how satisfied they are, how fast reports load, and who saw what. Today we release the biggest expansion to BI Pixie to help you scale your AI investment and take your Power BI semantic models to production with Copilot and Fabric data agents. BI Pixie assesses whether your semantic models are ready for AI, drafts the context they are missing, and creates benchmarks to test your AI against answers computed from your own data. Along with the expansion, we now offer a Free plan that assesses up to 500 semantic models, and a simplified flat pricing with no usage meters. AI Readiness is available in BI Pixie Workload for Microsoft Fabric or in the cloud version. - Tags: data-agent, ai-assessments, benchmarks, testing, production, monitoring - Contributor: Gil Raviv ### The Agents: Data Agent & Operations Agent in Practice - URL: https://medium.com/@jyotiprakash.behera89/the-agents-data-agent-operations-agent-in-practice-0ca3cdc462cb - Author: Jyotiprakash Behera - Published: 2026-04-25 - Summary: A solutions architect's deep dive into the two agents powering Fabric IQ - Data Agents and Operations Agents. Covers the execution chain, governance model, billing math, configuration levers, and the combined architecture where one agent detects and the other explains over a shared Ontology. - Tags: data-agent, fabric, ontology, operationagent - Contributor: Jyotiprakash Behera ### Prep data for AI vs. Fabric Data Agent Instructions: What Goes Where? - URL: https://www.jamesserra.com/archive/2026/10/prep-data-for-ai-vs-fabric-data-agent-instructions-what-goes-where/ - Author: James Serra - Published: 2026-10-01 - Summary: You have connected a [Power BI semantic model](https://learn.microsoft.com/en-us/fabric/data-science/semantic-model-best-practices) to a [Fabric Data Agent](https://learn.microsoft.com/en-us/fabric/data-science/concept-data-agent), and now you want to explain that People means Customers and Revenue means Net Sales Amount. Several configuration names sound relevant: [AI instructions](https://learn.microsoft.com/en-us/power-bi/create-reports/copilot-prepare-data-ai-instructions), [Data Agent instructions and data-source instructions](https://learn.microsoft.com/en-us/fabric/data-science/data-agent-configurations), and [example queries](https://learn.microsoft.com/en-us/fabric/data-science/data-agent-example-queries). Should you repeat the explanation everywhere to be safe? I would not take that approach, because these capabilities have different responsibilities and are not all available for semantic models. The useful distinction is between [preparing the semantic model for AI](https://learn.microsoft.com/en-us/power-bi/create-reports/copilot-prepare-data-ai) and configuring the agent that decides when to use it. - Tags: data-agent, prep-for-ai, context - Contributor: Sandeep Pawar ### The GINO Crisis: How Ambiguous Models Break Humans and LLMs — and the Case for Kimball 2.0 - URL: https://www.linkedin.com/pulse/gino-crisis-how-ambiguous-models-break-humans-llms-case-tony-smith-4mlpe/ - Author: Tony Smith - Published: 2026-04-16 - Summary: This article focuses on good database schema design. It highlights an emerging anti-pattern (GINO - "Gold in Name Only") whereby data engineering teams have "polished up" bronze data and moved it into Gold, with multi grain facts, normalised structures, outer joins etc, and left it to the Data Analyst to sort out. This is bad enough but it breaks when LLMs are brought in. The article then covers 6 straightforward techniques to simplify and optimise data models to increase success of NL2SQL platforms such as FDAs - Tags: fabric, fabricdataagents, nl2sql, kimball, starschema - Contributor: Tony Smith ### Using Microsoft Fabric Data Agent in Non-English Languages: A Practical Exploration - URL: https://medium.com/data-science-collective/using-microsoft-fabric-data-agent-in-non-english-languages-a-practical-exploration-bf1dcb8e4c02 - Author: Luca Zavarella - Published: 2026-01-02 - Summary: This article examines what Microsoft Fabric Data Agent's current non-English limitation means in practice, using Italian as a concrete business scenario. Rather than stopping at the official "English-first" guidance, it presents three pragmatic patterns for enabling multilingual experiences today: English instructions with translate-in/translate-out behavior, Copilot Studio as a multilingual front-end, and a translation gateway built around the Data Agent API. The goal is to help teams choose the right architecture for multilingual adoption without overestimating native language support. - Tags: data-agent, fabric, multilingual - Contributor: Luca Zavarella ### We Built the Benchmark. Now Let’s Evaluate the Fabric Data Agent for Real - URL: https://lucazavarella.medium.com/we-built-the-benchmark-now-lets-evaluate-the-fabric-data-agent-for-real-a8ffef236693 - Author: Luca Zavarella - Published: 2026-03-17 - Summary: This article shows how to move from a benchmark design to a real evaluation workflow for a Microsoft Fabric Data Agent. Starting from a 72-question benchmark built in a previous article for an Italian multilingual scenario, it explains how to complete the ground-truth dataset, run `evaluate_data_agent` on Fabric, inspect summary and row-level results, and use notebooks to operationalize the full process. A key insight is that part of the observed weakness may come not only from the Data Agent, but also from the evaluation layer itself. By inspecting the SDK source code and testing a stricter custom critic prompt, the article shows how evaluation reliability can improve significantly without changing the agent or the benchmark. Overall, the piece is a practical guide to benchmarking and evaluating Fabric Data Agents more rigorously, especially in multilingual business scenarios. - Tags: data-agent, fabric, evaluation, multilingual - Contributor: Luca Zavarella ### What We Learned Building a Real-World Fabric Data Agent - URL: https://www.linkedin.com/pulse/what-we-learned-building-real-world-fabric-data-agent-ankit-kumar-ass9e/ - Author: Ankit Kumar - Published: 2025-03-26 - Summary: 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. - Tags: data-agent, gql, graph, ontologies, tips - Contributor: Sandeep Pawar ### Why My Fabric Data Agent Returned the Wrong Number : Diagnosing a Silent Grounding Contamination Bug in Azure AI Foundry - URL: https://medium.com/@malharpawar/why-my-fabric-data-agent-returned-the-wrong-number-diagnosing-a-silent-grounding-contamination-865153f7b83f?sharedUserId=malharpawar - Author: Malhar Pawar - Published: 2026-09-10 - Summary: This article documents a production debugging session where an AI agent connected to Fabric Data Agent returned an incorrect number due to a File Search knowledge file contaminating the data grounding. It explains how to diagnose this using Azure AI Foundry traces and the architectural fix (moving static reference data into the system prompt and enforcing strict tool-gating) that resolved both correctness and response latency. - Tags: fabric, microsoftfoundry, fabricdataagent, ai, agenticai - Contributor: Malhar Pawar ### Why Semantic Models Behave Differently in Fabric Data Agents - URL: https://data-marc.com/2026/05/29/why-semantic-models-behave-differently-in-fabric-data-agents/ - Author: Marc Leljveld - Published: 2026-05-29 - Summary: Semantic Models behave differently inside Fabric Data Agents because they already contain rich business semantics, metadata, relationships, and AI instructions that the agent must respect. This makes NL2DAX fundamentally more opinionated than NL2SQL or NL2KQL. Blog explains how data agents work with semantic models. - Tags: semanticmodel, data-agent, best-practices - Contributor: Sandeep Pawar ### Why the Retirement of Fabric Data Agent Integration in Copilot in Power BI Is a Strategic Shift, Not a Step Back - URL: https://www.linkedin.com/pulse/why-retirement-fabric-data-agent-integration-copilot-power-mishra-cecqf/ - Author: Arun Prakash Mishra - Published: 2026-08-04 - Summary: Microsoft Fabric continues to evolve rapidly as the unified data platform for the AI era. One recent update that data leaders, architects, Power BI practitioners, and partners should pay close attention to is the upcoming retirement of the Fabric data agent integration in Copilot in Power BI. According to public updates, the integration between Fabric data agents and Copilot in Power BI is expected to retire on August 26, 2026. Importantly, this does not mean Fabric data agents are going away. Instead, it reflects a strategic shift in how conversational analytics and agentic data experiences are being surfaced across the Microsoft ecosystem. Retirement of Fabric data agent integration in Copilot in Power BI - Tags: data-agent, powerbi, powerbi-copilot, dataagent-vs-copilot - Contributor: Parv Chana ### Why Your Foundry Agent Works in the Playground But Fails for Every Other User The Identity Passthrough Problem Nobody Warns You About - URL: https://medium.com/@malharpawar/why-your-foundry-agent-works-in-the-playground-but-fails-for-every-other-user-the-identity-b6c0da5fad51 - Author: Malhar Pawar - Published: 2026-09-14 - Summary: This article documents why an Azure AI Foundry agent connected to a Microsoft Fabric Data Agent works perfectly for the builder but fails for every other user with tool_user_error or timeout errors. It explains the On-Behalf-Of (OBO) identity passthrough mechanism, maps out the four separate permission layers required across two different portals, and shows how a single Microsoft Entra security group fixes the problem permanently. - Tags: fabricdataagent, microsoftfoundry, ai, agenticai, powerbi, microsoftfabric - Contributor: Malhar Pawar --- ## Videos ### Analyzing Microsoft Fabric Data using an Azure AI Foundry Agent - YouTube: https://www.youtube.com/watch?v=Hw9PjqQWuok - Speaker: Ziggy Zulueta - Published: 2025-12-04 - Description: In this Microsoft Reactor session, Ziggy demonstrates how to analyze Microsoft Fabric data using a Microsoft Foundry Agent and surface insights through a conversational AI experience. This is the third and final part of a series where we transform unstructured data—such as product reviews and customer call recordings—into actionable insights using Microsoft Fabric, Foundry Agent Service, and Power BI. You’ll learn how to: Create a Fabric Data Agent to query lakehouse data in plain English Connect Microsoft Foundry Agents to Fabric for secure enterprise data access Deploy your AI-powered agent to Microsoft Teams for internal collaboration Use sample queries and SQL generation for real-time insights Understand the architecture behind Fabric lakehouse, pipelines, and notebooks - Tags: foundry, advanced - Contributor: Sandeep Pawar ### Building NFL Analytics with Fabric, Power BI, and AI Agents - YouTube: https://www.youtube.com/watch?v=CUAf4BonB-s - Speaker: Rob Kerr - Published: 2026-05-26 - Description: Video walkthrough building an end-to-end NFL analytics reference architecture in Microsoft Fabric using NFLVerse data, with accompanying GitHub repo. The video steps through the full pipeline (Bronze → Gold → semantic model) and compares two Fabric Data Agent patterns—Lakehouse (SQL) vs Semantic Model (DAX). We wrap by testing in Microsoft 365 Copilot and running agent evaluations to show how to iteratively improve natural language analytics quality. - Tags: dataagent, medallion, nfl, evaluations - Contributor: Rob Kerr ### Best Practices for Data Agents in Microsoft Fabric - YouTube: https://www.youtube.com/watch?v=VOIwu49f6BY - Speaker: Sandeep Pawar - Published: 2026-04-18 - Description: A deep dive into building and leveraging Data Agents within Microsoft Fabric — AI-powered autonomous systems that integrate with Fabric's lakehouse, warehouses, and semantic models to intelligently query, transform, and analyze data using natural language. This session will explore how Fabric's agent capabilities streamline data workflows and how to configure data agents with the right context to improve accuracy and reliability. - Tags: data-agent, how-to, bestpractices - Contributor: Parv Chana ### Configuring Fabric Data Agent to Accelerate Data to Decisions - YouTube: https://www.youtube.com/watch?v=OcndKpnv-2g - Speaker: Marc Bushong - Published: 2026-02-10 - Description: In this session, attendees will explore how to build and configure a Fabric Data Agent from the ground up. We’ll walk through practical commands and functions while working with data sourced from a Lakehouse, review data source setup and sample queries, and showcase how easily a Fabric Data Agent can be incorporated into a multi-agent workflow using Microsoft Foundry. - Tags: foundry, introduction, setup, lakehouse, advanced - Contributor: Sandeep Pawar ### Connect Data Agents to Teams with Copilot Studio - YouTube: https://www.youtube.com/watch?v=7ccFIUfjiIc - Speaker: Bradley Ball - Published: 2025-08-28 - Description: You've built your Retrieval Augmentation Generation, or RAG, pattern Data Agent in Microsoft Fabric, but now you want to share it with your organization! How do you do that? Fear not! Bradley Ball aka [‪@SQLBalls‬](https://www.youtube.com/@SQLBalls) has got you covered! We walk through Microsoft Fabric creating the Data Agent, to Copilot Studio creating a connected Agent, to Publishing and approving in Teams! - Tags: dataagent, copilotstudio, teams - Contributor: Sandeep Pawar ### Create your first Data Agent with SQL database in Fabric - YouTube: https://www.youtube.com/watch?v=yS_XdX8lrdE - Speaker: Sukhwant Kaur - Published: 2025-02-06 - Description: Learn to create low code/no code Data Agents in less than 5 minutes with SQL DB - Tags: sqldb, introduction, dataagent - Contributor: Sandeep Pawar ### Extend Fabric Data Agents with Python SDK End to End Tutorial - YouTube: https://www.youtube.com/watch?v=YJu9NQB3MuU - Speaker: Bradley Ball - Published: 2025-08-09 - Description: Let's walk through and End to End tutorial for extending an existing Data Agent with Bradley Ball, aka [‪@SQLBalls‬](https://www.youtube.com/@SQLBalls). In this tutorial we will use the first two links to get and clone the GitHub repo and to use the code to substitute our questions for those hard coded in the tutorial. We also extend the tutorial to make a change to move from hard coded questions to a more interactive Q & A application! - Tags: dataagent, pythonsdk, evaluation - Contributor: Sandeep Pawar ### Fabric Data Agent for Semantic Model - YouTube: https://www.youtube.com/watch?v=IImV292givo - Speaker: Greg Beaumont - Published: 2026-02-01 - Description: 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. - Tags: semanticmodel, setup - Contributor: Sandeep Pawar ### Fabric Data Agent Tutorial: Semantic Model + Prep for AI Makes All the Difference - YouTube: https://www.youtube.com/watch?v=1oPGjC1dP-4 - Speaker: View Boris Keckarovski’s profile Boris Keckarovski - Published: 2026-11-05 - Description: Building a Microsoft Fabric Data Agent is easy. Getting it to give good answers is the hard part. In this demo, we build a Fabric Data Agent on top of an Adventure Works semantic model and ask it the same questions twice: first on the baseline model, then after enhancing it with Prep Data for AI (simplified schema, verified answers, AI instructions) and agent instructions. The difference is clear. The answers become more concise, more direct, and aware of context, like partial-year data. We also try the new chart feature in Fabric Data Agents. Key takeaway: model first, Prep for AI second, agent setup third. - Tags: semantic-model, prepforai, data-agent - Contributor: Sandeep Pawar ### Fabric Data Agents 101 - YouTube: https://www.youtube.com/watch?v=ul16PjHNiVs - Speaker: Microsoft Fabric Community - Published: 2025-03-01 - Description: A beginner-friendly walkthrough covering the fundamentals of Fabric Data Agents — what they are, how to set them up, and how to start querying your data using natural language. - Tags: beginner, introduction, getting-started, data-agents - Contributor: Sandeep Pawar ### Fabric Data Agents and Beyond - YouTube: https://www.youtube.com/watch?v=Jc2fYdxRdEo - Speaker: Mathias Halkjær - Published: 2025-06-01 - Description: Explores the broader vision for Fabric Data Agents, including advanced use cases, multi-source data access, integration with Azure AI Agent Service, and how agents go beyond simple Q&A to enable enterprise-scale AI workflows. - Tags: advanced, architecture, azure-ai, enterprise, integration - Contributor: Sandeep Pawar ### Fabric Data Agents Explained: Building Secure, Data‑Grounded AI in Microsoft Fabric - YouTube: https://www.youtube.com/watch?v=kOrU8zdga00 - Speaker: Swetha Mannepalli and Mathias Halkjaer - Published: 2026-04-03 - Description: In this episode of Fabric Tech Talk Fridays, host Swetha Mannepalli is joined by Microsoft MVP Mathias Halkjaer to explore Fabric Data Agents. Learn what data agents are, how they differ from copilots, and how they bring trustworthy, data‑grounded AI to Microsoft Fabric. Watch a full demo covering security and governance, grounding agents on enterprise data, integrating with Microsoft 365 Copilot and external APIs, orchestrating multiple agents, and building AI solutions that respect existing access controls. Ideal for data leaders, architects, and anyone starting their AI agent journey in Fabric. - Tags: tutorial, fabricdataagent, data-agent, microsoftfabric - Contributor: Parv Chana ### Microsoft Fabric Data Agents Explained - YouTube: https://www.youtube.com/watch?v=mFoSVcj6tLw - Speaker: Guy in a Cube - Published: 2025-05-01 - Description: From query to conversation — demonstrates setting up a Fabric Data Agent, connecting it to a Lakehouse, customizing prompts, and using chat-based analytics to extract insights from your data in real time. - Tags: demo, lakehouse, prompts, analytics, chat - Contributor: Sandeep Pawar ### Fabric Data Agents Series (1/4): From Queries to AI Reasoning in Microsoft Fabric - YouTube: https://www.youtube.com/watch?v=hvwSTqQAUbg - Speaker: Jennifer Ratten - Published: 2026-04-16 - Description: This session kicks off our 4-part series on Microsoft Fabric Data Agents, exploring a major shift in how we interact with data — from writing queries to AI-driven reasoning under governance. In Part 1, we break down what Fabric Data Agents are (and are not), how they fit into the Microsoft Fabric ecosystem, and how the agent reasoning loop plans and executes grounded, trustworthy answers across governed data. You’ll learn why this shift matters, how it impacts Power BI developers and data teams, and what it takes to move from prompt-level experimentation to system-level AI thinking. 🚀 This is your starting point to understanding how semantic models, architecture, and governance come together to enable reliable, explainable, and scalable AI-powered analytics. 👉 Stay tuned for Parts 2–4, where we dive deeper into design patterns, architecture, and operating Data Agents at scale. 👍 Like, comment, and subscribe for more deep dives on Microsoft Fabric, Power BI, and AI in data. #MicrosoftFabric #PowerBI #FabricDataAgents #AIinAnalytics #DataPlatform - Tags: data-agent, tutorial, microosft-fabric - Contributor: Parv Chana ### Fabric Data Agents Series (2/4): Why Your Data Model Breaks AI in Microsoft Fabric - YouTube: https://www.youtube.com/watch?v=ZjJ89DtsrGg - Speaker: Jennifer Ratten - Published: 2026-04-26 - Description: 👉 If your data model isn’t solid, your AI won’t be either. In Part 2 of our Microsoft Fabric Data Agents series, we focus on the foundation that makes or breaks AI: your semantic model and data design. This session shows how to build AI-ready data foundations so Fabric Data Agents can deliver accurate, consistent, and trustworthy results — not hallucinations or ambiguity. 🎯 What you’ll learn: ✔️ Why naming conventions and clear definitions are critical for AI reasoning ✔️ How explicit measures improve consistency and trust ✔️ The role of star schema design in scalable AI analytics ✔️ Common failure modes that break Data Agents ✔️ Practical Fabric-native fixes to improve grounding quality Most AI projects don’t fail because of AI — they fail because of bad data modeling. This session gives you the frameworks to fix that. 🚀 Whether you're a Power BI developer, data engineer, or architect, this is your blueprint for moving from experiments → production-ready AI systems. 👉 Watch Part 1 to understand Fabric Data Agents fundamentals 👉 Continue with Parts 3 & 4 to master architecture and governance at scale 👍 Subscribe for more deep dives on Microsoft Fabric, Power BI, and AI-driven data platforms #MicrosoftFabric #PowerBI #DataModeling #FabricDataAgents #AIinAnalytics - Tags: data-agent, semanticmode, microsoftfabric, howtodataagent, learndataagent - Contributor: Parv Chana ### Fabric Data Agents Series (3/4): How to Use Fabric Data Agents in Real Apps #vfpug - YouTube: https://www.youtube.com/watch?v=PkLvqgIp15I - Speaker: Jennifer Ratten - Published: 2026-05-08 - Description: Understanding Data Agents is one thing… using them in real applications is another. In Part 3 of our Microsoft Fabric Data Agents series, we focus on how to actually implement and consume Data Agents in production scenarios. This session breaks down the most effective architectural patterns to bring Data Agents to life across different audiences — from business users to developers and enterprise systems. 🎯 What you’ll learn: ✔️ How Copilot experiences work with Fabric Data Agents ✔️ Building custom business Q&A applications ✔️ Enabling agent-to-agent workflows using MCP ✔️ Designing enterprise APIs with GraphQL + agent translation ✔️ How to choose between Data Agent APIs, MCP, and GraphQL based on your use case and risk profile This is where strategy meets execution — helping you move from experimentation → scalable, real-world AI solutions. - Tags: tutorial, data-agents, microsoftfabric - Contributor: Parv Chana ### Fabric Data Agents Series (4/4): Governance Guide - Can You Trust Your AI? 🔐 - YouTube: https://www.youtube.com/watch?v=8EVDqbi25Eg - Speaker: Jennifer Ratten - Published: 2026-05-15 - Description: In Part 4 of our Microsoft Fabric Data Agents series, we focus on the most critical aspect of AI adoption: governance, security, and trust. This session shows how to design compliant, secure, and auditable Data Agent experiences so your AI solutions don’t just work — they work responsibly at scale. 🎯 What you’ll learn: ✔️ Execution identity — understanding who the agent acts as ✔️ Enforcing Row-Level Security (RLS) and Object-Level Security (OLS) ✔️ Building auditability and traceability into AI workflows ✔️ Preventing data oversharing and leakage ✔️ Applying governance best practices aligned with Microsoft Purview concepts - Tags: tutorial, data-agent, fabricdataagent, microsoftfabric - Contributor: Parv Chana ### From On Prem SQL to Natural Language Queries with Fabric Mirroring & Data Agents - YouTube: https://www.youtube.com/watch?v=84CjvmfNGg0 - Speaker: Rob Kerr - Published: 2026-04-20 - Description: Video showing how to go from on‑prem SQL Server → Fabric Mirroring → Data Agent so users can ask plain‑English questions over real data. Detailed walk through of the configuration, resulting in a reusable example of putting Fabric’s AI features to work on existing systems. - Tags: dataagent, mirroring, sqlserver - Contributor: Rob Kerr ### How to Set Up Fabric Data Agents in Microsoft Fabric - YouTube: https://www.youtube.com/watch?v=fAKnVJh5ciI - Speaker: David Alzamendi - Published: 2025-06-04 - Description: Discover how to configure Fabric Data Agents to streamline and manage your data movement across environments in Microsoft Fabric. In this tutorial, we’ll guide you through the installation, setup, and key use cases for Data Agents, helping you connect to on-premises sources and automate secure data flows. Perfect for Fabric admins and data engineers looking to enable hybrid data scenarios with ease. Hi, I’m David, the Managing Director of Level Up Your Data based in Brisbane, Australia and a Microsoft Data Platform MVP. I am passionate about the positive impact data can have on our lives, businesses, world economies, and the environment and enjoy sharing my knowledge with you. - Tags: data-agent, introduction - Contributor: Sandeep Pawar ### How to use Data Agent Example Queries - YouTube: https://www.youtube.com/watch?v=v0mD01QP5gY - Speaker: Bradley Ball - Published: 2026-05-26 - Description: Example Queries are THE key value differentiator between Microsoft Fabric Data Agents and all other RAG agents you can build, so let's dive into this topic with Bradley Ball, aka [‪@SQLBalls‬](https://www.youtube.com/@SQLBalls) , and look and how we can use them! - Tags: data-agent, tsql, few-shot, example-queries, accuracy - Contributor: Sandeep Pawar ### Introduction to Microsoft Fabric Data Agents - YouTube: https://www.youtube.com/watch?v=SZSQ70sytlU - Speaker: Pragmatic Works - Published: 2025-04-01 - Description: Covers what Fabric Data Agents are, how they use generative AI for Q&A over your data, prerequisites, setup process, connecting semantic models, and how to publish agents for broader use across Microsoft 365 Copilot and Teams. - Tags: introduction, demo, setup, copilot, semantic-model - Contributor: Sandeep Pawar ### Les Data Agents dans Microsoft Fabric - YouTube: https://www.youtube.com/watch?v=8R6qF1iwnkE - Speaker: Akram Drid - Published: 2026-02-05 - Description: Dans l’océan des données, voir clair change tout. Sur Phare Data, on décrypte les services de data, d’analytics et d’IA, avec un ton accessible, des choix techniques assumés, et toujours une touche d’air marin. Que vous soyez architecte, analyste, data engineer, product owner, ou simplement curieux, Phare Data vous accompagne pour comprendre les enjeux réels, éclairer les compromis et prendre de meilleures décisions et parfois avec le cri des mouettes en bruit de fond. - Tags: tutorial, dataagent, french, introduction - Contributor: Sandeep Pawar ### Microsoft Fabric の AI 機能デモ - YouTube: https://www.youtube.com/watch?v=TyVWmNd3bFA - Speaker: Ryoma Nagata - Published: 2025-10-15 - Description: このビデオは、Fabric の ミラーリング、ショートカット、AI 関数、データエージェントやCopilotに焦点をあてています。 データの統合にはじまり、AIを使用した顧客フィードバックの感情分析や、AIエージェントによるデータ分析をFabric上で行う方法を紹介します。 English :This video focuses on Fabric features such as Mirroring, Shortcuts, AI functions, Data Agents, and Copilot. It introduces how to start with data integration, use AI for sentiment analysis of customer feedback, and perform data analysis on Fabric with AI agents. - Tags: ai-function, data-agent, shortcut, mirroring, demo - Contributor: Ryoma Nagata ### Microsoft Fabric: Connect Data Agent to Azure AI Foundry - YouTube: https://www.youtube.com/watch?v=nqUt-wCYY2M - Speaker: Bradley Ball - Published: 2025-08-26 - Description: Data agent in Microsoft Fabric transforms enterprise data into conversational Q&A systems. It enables users to interact with their data through chat, to uncover actionable insights. One way to consume Fabric data agent is through Azure AI Agent Service, a core component of Azure AI Foundry and Bradley Ball, aka [‪@SQLBalls‬](https://www.youtube.com/@SQLBalls) , has got you covered!! - Tags: foundry, advanced - Contributor: Sandeep Pawar ### Microsoft Fabric Data Agents LIVE Demo 🚀 | Real AI Use Cases Explained #vfpug - YouTube: https://www.youtube.com/watch?v=ARg5xgT1YJA - Speaker: Jennifer Ratten - Published: 2026-05-29 - Description: 👉 Getting insights from your data shouldn’t feel like solving a puzzle. In this session, Jennifer demonstrates several Microsoft Fabric Data Agents in action, showcasing how conversational AI experiences can transform the way users interact with governed data. This session focuses on practical, real-world examples of how Fabric Data Agents enable users to ask questions naturally and receive grounded, trustworthy answers powered by Microsoft Fabric. 🎯 What you’ll learn: ✔️ How Fabric Data Agents work in real scenarios ✔️ Conversational access to governed enterprise data ✔️ AI-powered self-service analytics patterns ✔️ Practical Power BI and Microsoft Fabric integrations ✔️ Real-world approaches for delivering trusted AI experiences Whether you're a Power BI developer, Fabric practitioner, analyst, or architect, this session helps bridge the gap between AI concepts and real business value. 🚀 No AI background required — just curiosity about the future of data experiences. - Tags: tutorial, data-agent, microsoftfabric - Contributor: Parv Chana ### Microsoft Fabric: How to use Data Agent Example Queries - YouTube: https://www.youtube.com/watch?v=v0mD01QP5gY - Speaker: Bradley Ball - Published: 2026-04-23 - Description: Example Queries are THE key value differentiator between Microsoft Fabric Data Agents and all other RAG agents you can build, so let's dive into this topic with Bradley Ball, aka [‪@SQLBalls‬](https://www.youtube.com/@SQLBalls) , and look and how we can use them! - Tags: data-agent, tutorial, how-to - Contributor: Parv Chana ### Microsoft Fabricで考える非構造データのAI活用 - YouTube: https://www.youtube.com/watch?v=dTJpMDzFFSI - Speaker: Ryoma Nagata - Published: 2026-03-31 - Description: このビデオは、G-Corporationの永田凌真氏によって紹介され、Microsoft Fabricエコシステム内で非構造データを活用するAIの活用に焦点を当てています。セッションでは、AI FunctionsやData Agentを含む最新のデータアーキテクチャとAI実装戦略について、技術的な詳細を深く掘り下げています English : This video, presented by Ryomaru Nagata from G-Corporation, focuses on leveraging AI for unstructured data within the Microsoft Fabric ecosystem. The session provides a technical deep dive into modern data architecture and AI implementation strategies, including AI Functions and Data Agent - Tags: data-agent, unstructured-data, ai-functions, medallionarchitecture - Contributor: Sandeep Pawar ### Optimizing the Costs of Fabric Data Agents - YouTube: https://www.youtube.com/watch?v=u5debnBHFec - Speaker: Bas Land - Published: 2026-02-04 - Description: In this video you will learn how to find the costs of Fabric Data Agents, by looking at the Fabric Capacity Metrics App. - Tags: optimization, capacitymetricsapp - Contributor: Sandeep Pawar ### Publish Data Agents Directly to Microsoft 365 - YouTube: https://www.youtube.com/watch?v=yCD8-qAIT2I - Speaker: Bradley Ball - Published: 2025-12-18 - Description: It's here! Fresh off of Microsoft Ignite 2025 we can now publish Data Agents directly to Microsoft 365 and Bradley Ball, aka [‪@SQLBalls‬](https://www.youtube.com/@SQLBalls) , has got you covered! This is a super simple process and we will walk through how to publish, what the interface looks like, and how to share it with Microsoft Teams! - Tags: m365copilot - Contributor: Sandeep Pawar ### Skip navigation fabric data agent Create Avatar image Turning Data into Insights with Copilot and Data Agents in Microsoft Fabric - YouTube: https://www.youtube.com/watch?v=UWPADSmDAl4 - Speaker: Virginia Roman - Published: 2025-08-09 - Description: We will explore AI functions in notebooks, which make it easy to apply enrichment such as summarization, sentiment analysis, and entity extraction with a single line of code. You will also see how AI-powered transforms on OneLake shortcuts can automatically process text files for summarization, translation, or PII detection without building pipelines. Finally, we will show how Data Wrangler provides an interactive way to clean and shape your data inside notebooks while generating reusable code. Through a live demo, you will see how these capabilities combine to help you deliver insights and intelligent features quickly for your hackathon project. - Tags: copilot - Contributor: Sandeep Pawar ### What’s Next for Semantic Models in Fabric Data Agent - YouTube: https://www.youtube.com/watch?v=nIdjcuxQ_5g - Speaker: Virginia Roman - Published: 2026-10-20 - Description: Get a preview of what’s coming for Power BI semantic models in Fabric Data Agents. We’ll walk through improvements to configuration capabilities, response quality and consistency, and end-to-end latency - giving users greater control and helping them build faster, more reliable data agents that deliver better answers over their Power BI data. We will also share the best practices to get the most out of your data agents. - Tags: semantic-model, data-agent, prepforai, semanticintelligence - Contributor: Sandeep Pawar ### Wiring AI Agents to Enterprise Data with Azure AI Foundry + Fabric - YouTube: https://www.youtube.com/watch?v=4JZEkUpcR04 - Speaker: Pablo's AI Corner - Published: 2025-12-20 - Description: This demo shows one concrete way to design a multi-agent system using Azure AI Foundry and Microsoft Fabric. - Tags: foundry, multi-agent, advanced - Contributor: Sandeep Pawar --- ## Resources ### Agentic App with Fabric (incl Data Agents) - URL: https://github.com/Azure-Samples/agentic-app-with-fabric - Category: repository - Description: Agentic Banking App is an interactive web application designed to simulate a modern banking dashboard. Its primary purpose is to serve as an educational tool, demonstrating: How SQL-based databases are leveraged across different types of workloads: OLTP, OLAP, AI workloads. How agile AI-driven analysis and insight discovery can be enabled via prescriptive data models in Fabric. How easy it is possible to integrate other Fabric workloads (e.g., Report, Data Agent, Notebook) leveraging that data model. Image Through a hands-on interface, users can see the practical difference between writing a new transaction to the database, running complex analytical queries on historical data, and using natural language to ask an agent to query the database for them. - Tags: agenticapp, database, sqldb, oltp, hands-on, workshop, project, dataagent, ai - Contributor: Sandeep Pawar ### Data Agent Governance and Security Accelerator Using Purview - URL: https://github.com/microsoft/Data-and-Agent-Governance-and-Security-Accelerator/blob/main/README.md#start-here - Category: repository - Description: Enable Microsoft Purview Data Security Posture Management (DSPM) for AI across Microsoft 365 Copilot, Microsoft Foundry, Microsoft Fabric, and custom AI solutions with a spec-driven deployment and governance workflow. - Tags: data-agent, dspm, governance, purview, foundry - Contributor: Sandeep Pawar ### Data Agent Python SDK Notebooks - URL: https://github.com/microsoft/fabric-samples/tree/main/docs-samples/data-science/data-agent-sdk - Category: sample-code - Description: Notebooks to evaluate, automate, test data agents - Tags: data-agent, notebooks, pythonsdk - Contributor: Sandeep Pawar ### Data Agent Workshop : FabCon EU 2025 - URL: https://github.com/msft-shreyas/fabconeu-2025-dataagent-tutorial - Category: repository - Description: Hands-on workshop material from FabCon Vienna 2025 on building data agents - Tags: workshop, data-agent, hands-on, repository - Contributor: Sandeep Pawar ### Microsoft Fabric Community Forum - URL: https://community.fabric.microsoft.com/ - Category: Community - Description: Join the Microsoft Fabric community to ask questions, share solutions, and connect with other data agent builders. - Tags: community, forum, support - Contributor: Sandeep Pawar ### Fabric Data Agent CI/CD Testing Template - URL: https://github.com/FC2026-DeepDiveFabricCICD/data-agent-ci-demo - Category: repository - Description: Automated testing framework for Microsoft Fabric Data Agents using [PromptFoo](https://promptfoo.dev/) with Azure DevOps CI/CD integration. - Tags: data-agent, ci-cd, deployment, operationalize, promptfoo - Contributor: Sandeep Pawar ### Fabric Data Agent Demo — Wide World Importers - URL: https://github.com/ptprussak/wwimporters - Category: repository - Description: Two sample Microsoft Fabric data agents built on the WideWorldImportersDW data warehouse. A simple agent with minimal instructions silently returns wrong answers for complex queries, while an advanced agent with full data model documentation handles them correctly — same LLM, same data, different instructions. The demo proves that agent instruction quality is the single biggest lever for accuracy when building data agents over enterprise data warehouses with SCD2 dimensions, bridge tables, and weighted allocations. - Tags: data-agent, hands-on, demo, end-to-end, project - Contributor: Sandeep Pawar ### Fabric Data Agent Router - URL: https://github.com/PatrickGallucci/fabric-data-agent-router - Category: sample-code - Description: Routes natural language queries to the appropriate Microsoft Fabric Data Agent using Azure AI Foundry Agent Service with function calling. - Tags: data-agent, foundry - Contributor: AA ### Fabric Data Agent Embedding Template - URL: https://v0.app/templates/embed-a-fabric-data-agent-in-minutes-i10GRG9zv0X - Category: sample-code - Description: An educational web app template demonstrating how to embed a Microsoft Fabric Data Agent into a web application using Service Principal authentication. It walks users through every configuration step required — Azure app registration, Fabric workspace permissions, role assignments, and securely wiring tenant, client, and secret values into the app. Users can: - Drop in credentials to test existing data agents directly - Fork the template to build their own embedded agent app - Hand it to a coding assistant as a working example to replicate the pattern in their own applications. **Roadmap**: If there's interest, future versions will expand into showcasing more of what's possible when embedding Fabric Data Agents in custom apps such as: - Additional design themes and UI styles - More custom agent interface capabilities - Support for data agent teams - Tags: data-agent, fabric - Contributor: Brendan Daly ### Fabric Data Agents Lab - URL: https://github.com/hamoodaleem_microsoft/fabric-agents-lab - Category: tutorial - Description: Welcome to the Fabric Agents Lab — a hands‑on experience where you’ll build and interact with an AI-powered data agent using Microsoft Fabric. You’ll explore real-time ecommerce data from Nova Mart, enrich insights with dimensional context, and see how natural language questions can drive deep analytical results. By the end, you’ll understand how to design, refine, and operationalize a Fabric Agent that delivers fast, business-ready insights to any user. - Tags: data-agent, hands-on, tutorial - Contributor: Sandeep Pawar ### Fabric Data Agent Sample Notebooks - URL: https://github.com/microsoft/fabric-samples - Category: Code Samples - Description: A collection of Jupyter notebooks and code samples demonstrating various data agent patterns and use cases in Microsoft Fabric. - Tags: samples, notebooks, code - Contributor: Sandeep Pawar ### Hands On : Build a Direct Lake Model with Data Agents with 275M+ Healthcare Records - URL: https://github.com/isinghrana/fabric-samples-healthcare/tree/main/analytics-bi-directlake-starschema - Category: repository - Description: 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](https://data.cms.gov/provider-summary-by-type-of-service/medicare-part-d-prescribers/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 - Tags: hands-on, dataagent, directlake, semanticmodel, repo - Contributor: Sandeep Pawar ### Ontology with Data Agent - URL: https://github.com/Chalmers2000/build-fabric-ontology-demo - Category: repository - Description: This project provides a complete, end‑to‑end walkthrough for building a Microsoft Fabric Ontology demo—either by installing a ready‑made healthcare example or by creating your own custom ontology, lakehouse tables, demo data, and graph queries. It shows how to use tools like VS Code, GitHub Copilot, Semantic Link Labs notebooks, and the Fabric Ontology Playground to generate RDF models, orchestrate table creation, build a graph database, and construct multi‑hop GQL queries that highlight the strengths of graph reasoning. It also guides you through creating a Fabric Data Agent powered by your ontology, including AI instructions and sample prompts, enabling a fully functional demo environment in under an hour. - Tags: iq, ontology, data-agent, hands-on, graph, gql - Contributor: Sandeep Pawar --- ## Events ### Designing AI‑Ready Data Surfaces: Why Agents Expose Your Weak Spots - URL: https://www.meetup.com/vancouver-fabric-and-power-bi-user-group/events/314122746/ - Date: 2026-04-23 - Location: Virtual (Teams) - Type: conference - Description: Part 2 or 4: Build the semantic and data foundations that make agents reliable. This workshop translates modeling best practices into agent-ready guidance: naming and definitions, explicit measures, star schema discipline, and how to prevent ambiguous data surfaces. Includes common failure modes and Fabric-native remediation strategies to improve grounding quality. - Tags: meetup, data-agent, msft-fabric, microsoftfabric - Contributor: Parv Chana ### Designing Trusted Fabric Data Agents - Part 1 - URL: https://www.meetup.com/vancouver-fabric-and-power-bi-user-group/events/314122449/ - Date: 2026-04-16 - Location: Virtual - Type: meetup - Description: This four‑part series guides attendees through the intricacies of Microsoft Fabric Data Agents - from understanding how agents reason over data, to designing AI‑ready data foundations, selecting the right consumption architectures, and operating agents safely at scale. Participants will learn how to move beyond prompt‑level experimentation to system‑level thinking, how agent reasoning, semantic modeling, architectural patterns, and governance controls work together to produce reliable, explainable, and compliant AI‑driven outcomes. Each session builds on the last, equipping teams with practical frameworks, patterns, and checklists to confidently deploy Fabric Data Agents across diverse audiences while managing risk, trust, and performance. Part 1 or 4: A guided tour of why Fabric Data Agents represent a shift from human-authored queries to AI-authored execution logic under guardrails. Learn what a data agent is (and is not), how it fits into the Fabric ecosystem, and how the agent reasoning loop plans and executes grounded answers across governed Fabric artifacts. - Tags: meetup, fabric, data-agent, fabricdataagents - Contributor: Parv Chana ### Microsoft Fabric Community Conference 2026 - URL: https://fabricconf.com - Date: 2026-06-15 to 2026-06-18 - Location: Las Vegas, NV - Type: conference - Description: The annual Microsoft Fabric Community Conference featuring sessions on data agents, real-time analytics, and the latest Fabric innovations. - Tags: conference, fabric-conf, annual - Contributor: Sandeep Pawar ### Fabric Data Agent in a Day - URL: https://lodestar.eu/fabric-data-agent-in-a-day/ - Date: 2026-05-20 - Location: In person, Milan, Italy - Type: conference - Description: Fabric Data Agent in a Day is a hands-on half-day workshop on Microsoft Fabric Data Agent, scheduled for 20 May 2026 in Milan, designed to show how to move from raw data ingestion to conversational agents that can answer business questions in natural language. During the session, participants populate a Lakehouse and a SQL Database in Fabric, build a first SQL-based Data Agent, make it more effective for Italian-language queries, apply Row Level Security, and measure its performance with Microsoft’s evaluation tools. The workshop then moves to a second agent built on a semantic model with DAX, so attendees can compare the semantic-model approach with the SQL-based one. Overall, the workshop is meant for data and BI professionals who want a practical introduction to building secure, multilingual, end-to-end conversational AI experiences on top of Microsoft Fabric data, using patterns that are closer to real projects than to simple demos. - Tags: workshop, fabric, data-agent - Contributor: Luca Zavarella ### From Power BI to Conversational AI: Building Data Agents That Scales - URL: https://sqlsaturday.com/2026-03-21-sqlsaturday1127/ - Date: 2026-03-21 - Location: Atlanta - Type: conference - Description: Your Power BI semantic models already contain trusted business logic, metrics, and relationships. What if those same models could answer questions in natural language across Teams, Excel, and M365 Copilot without rebuilding everything? In this session, you'll see the complete journey from a standard Power BI semantic model to a conversational data agent deployed across multiple surfaces. We'll walk through: Preparing your semantic model for AI: Adding descriptions, AI instructions, and verified answers directly in Power BI Desktop Creating Fabric Data Agents: Turning your semantic model into an intelligent assistant with proper guardrails Deploying across M365: Making your agent accessible in Excel, Teams, and M365 Copilot Through a live demonstration using a real semantic model, you'll see how to handle time intelligence, variance calculations, and business-specific definitions so the AI understands your metrics the way your users do. We'll also cover what actually works (and what doesn't) when moving from visual analytics to conversational experiences. This isn't about replacing Power BI reports. It's about extending the work you've already done into new interaction patterns where they add real value. - Tags: sqlsaturday, dataagent - Contributor: Sandeep Pawar ### Fabric Data Agents - URL: https://www.meetup.com/power-bi-user-group-wellington-nz/events/314897993/ - Date: 2026-06-25 - Location: Virtual - Type: conference - Description: Fabric data agents are now generally available in Microsoft Fabric, and they give teams a way to build conversational Q&A experiences over data sources like Power BI semantic models. But the real work is not just creating the agent. It is shaping the semantic model, instructions, examples, and feedback loop so the answers are robust. Which is why our next Wellington Power BI & Fabric User Group session is on Fabric data agents: what they are, where they fit, and how to get better results from them. - Tags: meetup, data-agent, virtual, howto - Contributor: Parv Chana ### Get You #MicrosoftFabric Data Agent Tuned - URL: https://www.linkedin.com/safety/go/?url=https%3A%2F%2Flnkd.in%2FeXyRP7Hm&urlhash=BK5G&mt=lzGF3P0kQhZ_pfTA03FZ5_CgvChKizjeJfCTOu39RRFrjvWz2cPyiwKKqvjSmkfxo6yoZEhV6Bv2B5ItdvBFza0Za5K_u191C3V1Y3pY-HGFMsHsc1k&isSdui=true&lipi=urn%3Ali%3Apage%3Ad_flagship3_detail_base%3BxZDZOWyVR7uA0vt2Jv4i6g%3D%3D - Date: 2026-08-04 - Location: Virtual - Type: meetup - Description: The Beyond the Prompt: Tuning Microsoft Fabric Data Agents for Flawless Results is presented by Thimantha Vidanagamage and hosted by Adriano da Silva at the Microsoft Data and AI South Florida user group. 🎯 This presentation provides you with a blueprint on how to implement Microsoft Fabric Data Agents by covering the key concepts, best practices, and providing practical examples. 💡 Register Right Now to learn more about it. 💡 We will show you how to make this a reality at the Microsoft Data and AI South Florida User Group (DataAISF). - ABSTRACT: As organizations race to deploy AI Agents, it quickly becomes clear that standard prompt engineering isn't enough. To achieve production-grade accuracy, you have to go beyond the prompt and fundamentally change how you feed your data layers to the AI. 📌 TOPICS COVERED: * Microsoft Fabric Data Agents * Ontology * Embedding Semantic Metadata * and much more In Microsoft Fabric, your choice of data artifact directly dictates your agent's reasoning style and native language. In this session, we will deep-dive into how Fabric Data Agents interact with four distinct data paradigms: Semantic Models, Ontology, Data Warehouses, and Lakehouses. You will walk away with an actionable blueprint showing you exactly how to write context rules, embed semantic metadata, and supply technical query examples to ensure your Fabric Data Agents deliver flawless, trusted results every time. - Tags: data-agent, tuning, optimization - Contributor: Sandeep Pawar ### Less Puzzles, More Answers: Teach Your Data to Talk Back with Fabric Data Agents - URL: https://www.meetup.com/vancouver-fabric-and-power-bi-user-group/events/314861392/ - Date: 2026-05-28 - Location: Virtual - Type: conference - Description: Getting insights from your data shouldn’t feel like solving a puzzle. In this session, Jennifer will demo several Microsoft Fabric Data Agents so you can see them in action. This session is ideal for Power BI and Fabric practitioners who want to turn governed data into conversational, self‑service answers using real‑world AI patterns. No AI background required. Familiarity with Fabric or Power BI is helpful but not mandatory. - Tags: meetup, fabricdataagent, data-agent, microsoft-fabric - Contributor: Parv Chana ### Operating & Architecting with Data Agents: Patterns, Risk, and Trust at Scale - URL: https://www.meetup.com/vancouver-fabric-and-power-bi-user-group/events/314124785/ - Date: 2026-05-14 - Location: Virtual - Type: meetup - Description: This four‑part series guides attendees through the intricacies of Microsoft Fabric Data Agents - from understanding how agents reason over data, to designing AI‑ready data foundations, selecting the right consumption architectures, and operating agents safely at scale. Part 4 or 4: Design trusted, compliant conversational access to governed data. This workshop focuses on execution identity decisions, RLS/OLS enforcement, auditability, and using governance practices (including Purview alignment concepts) to prevent oversharing. Participants leave with a practical checklist for deploying agents safely across audiences. - Tags: meetup, fabric, data-agent - Contributor: Parv Chana ### Part 3 / 4: Fabric Data Agent Architecture Patterns: Choosing the Right Consumption Path - URL: https://www.meetup.com/vancouver-fabric-and-power-bi-user-group/events/314124774/ - Date: 2026-05-07 - Location: Virtual (Teams) - Type: conference - Description: Part 3 or 4: Explore the most common and successful architectural patterns for consuming Fabric Data Agents: native Copilot experiences, custom business Q&A apps, agent-to-agent developer workflows via MCP, and enterprise data APIs with optional agent translation. Learn how to choose between Data Agent API, MCP server, and GraphQL depending on your consumers and risk profile. - Tags: meetup, data-agent, architectpattern, microsoftfabric - Contributor: Parv Chana --- ## Tools ### Data Agent Automation Using Python SDK - URL: https://github.com/microsoft/fabric-samples/blob/main/docs-samples/data-science/data-agent-sdk/Fabric-DataAgent-Automation-Library-sample.ipynb - Category: library - Description: Notebook to automate creation, testing and updating data agent using Python SDK in Fabric notebook. - Tags: python, testing, automation, dataagent, notebook - Contributor: Sandeep Pawar ### Data Agent Client - Teams App - URL: https://github.com/arielelevy/dataagent-client - Category: framework - Description: 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 - Tags: teams, dataagent, semanticmodel, foundry, application, repo, multi-agent - Contributor: Sandeep Pawar ### Data Agent External Client Python - URL: https://github.com/microsoft/fabric_data_agent_client/tree/main - Category: library - Description: A standalone Python client for calling Microsoft Fabric Data Agents from outside of the Fabric environment using interactive browser authentication. ⚠️This is in Preview and API can change until GA. - Tags: python, sdk, external, dataagent - Contributor: Sandeep Pawar ### Data Agent Inspector - URL: https://data-agent-inspector.streamlit.app/ - Category: utility - Description: App to review data agent diagnostic file. - Tags: diagnostic, dataagent, application, testing, debugging - Contributor: Sandeep Pawar ### Data Agent MCP - URL: https://learn.microsoft.com/en-us/fabric/data-science/data-agent-mcp-server - Category: library - Description: The Model Context Protocol (MCP) server is an emerging standard in the AI landscape that allows AI systems to discover and interact with external tools in a structured way. It plays a critical role in enabling AI models to access and use external knowledge and capabilities. By using MCP servers, AI systems can extend beyond their own data and reasoning. MCP servers provide a way to expose tools and services to AI systems in a consistent, discoverable manner. They help organizations integrate their knowledge into AI workflows. - Tags: data-agent, mcp, vscode - Contributor: Sandeep Pawar ### Fabric Data Agent Ground Truth Generator - URL: https://github.com/jennratten/fabric-data-agent-gallery/blob/main/samples/fabric_data_agent_ground_truth_generator_template.ipynb - Category: testing - Description: This tool is a reusable notebook template which creates ground truth evaluation datasets for Fabric data agents over any Power BI / Fabric semantic model, including Direct Lake semantic models, enabling the data agent evaluation process to be more automated. The primary purpose of the notebook is to support the evaluation of Fabric data agents by generating ground truth datasets that can be used to measure answer quality, accuracy, and performance. - Tags: python, testing, data-agent, template, notebook - Contributor: Jennifer Ratten ### Fabric Data Agent Latency Analyzer - URL: https://github.com/gregnatkatz/FabricAnalyzer/tree/MAIN - Category: library - Description: **What it is:** A locally-installed diagnostic tool that connects to your Microsoft Fabric workspace, analyzes your Data Agents using a 12-agent AI pipeline (GPT-5.4 + DeepSeek V3.2 Speciale), identifies latency bottlenecks, runs Monte Carlo simulations, and generates paste-ready fix artifacts with PDF reports. I built this as an open-source project to help Fabric developers diagnose and fix Data Agent performance issues. **What it isn't:** This is not a monitoring dashboard, a replacement for Fabric Capacity Metrics, or a general-purpose BI tool. It's a focused diagnostic analyzer that tells you why your Data Agent is slow and exactly how to fix it. **Why it matters:** Every Fabric Data Agent starts with default configuration. Without validation, agents accumulate anti-patterns — schema bloat, ambiguous measures, missing verified answers, poor routing instructions — that compound into 3-4x latency above SLA. This tool finds those issues before your users do. - Tags: data-agent, tool, latency - Contributor: Sandeep Pawar ### Semantic Link Labs - URL: https://github.com/microsoft/semantic-link-labs - Category: Framework - Description: An open-source toolkit for building semantic layers and connecting data agents to structured data sources in Microsoft Fabric. - Tags: semantic-link, framework, open-source - Contributor: Sandeep Pawar ### Semantic Model Data Agent Readiness Analyzer - URL: https://github.com/SoomroFarhanH/SemanticModelBPforAI/blob/main/SemanticModel_DataAgent_Readiness_v2.2.ipynb - Category: utility - Description: 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. - Tags: semanticmodel, dataagent, readinessanalyzer - Contributor: Soomro Farhan --- ## LinkedIn Posts ### Building a Fabric Data Agent with On‑Premises SQL Server Data - LinkedIn URL: https://www.linkedin.com/pulse/building-fabric-data-agent-onpremises-sql-server-pablo-junco-boquer-1xv8e/?trackingId=vLGBvPezTfOuuLx0FYkj1g%3D%3D - Author: Pablo Junco Boquer - Submitted: 2026-04-18 - Description: Many organizations still rely on on‑premises SQL Server for core operational workloads — finance, billing, ERP, manufacturing, and regulatory systems — that cannot be easily migrated to the cloud. At the same time, the business is demanding: Conversational access to data (“Ask the data” experiences) AI‑powered insights without building fragile ETL pipelines Faster time‑to‑value from analytics and AI Strong governance, security boundaries, and system ownership Microsoft Fabric addresses this challenge by allowing organizations to bring AI to their data before moving their data to AI. By leveraging SQL Server mirroring into Microsoft Fabric, organizations can continuously replicate on-premises data into OneLake, making it immediately available for analytics and AI—without disrupting source systems. On top of this foundation, semantic models and Fabric Data Agents enable governed, natural-language interactions powered by Microsoft Copilot. - Tags: data-agent, on-prem, sql - Contributor: Sandeep Pawar ### 𝗖𝗵𝗮𝘁 𝘄𝗶𝘁𝗵 𝘆𝗼𝘂𝗿 𝗱𝗮𝘁𝗮 in Copilot, Data Agents or Databricks One? 🤖 - LinkedIn URL: https://www.linkedin.com/posts/davidkofod_chat-with-your-data-david-hanna-activity-7450977881997873152-Qd0j?utm_source=share&utm_medium=member_desktop&rcm=ACoAAACXVe0BAgnEWy4VG5-Uls4-c7M2P6w-pWQ - Author: David Kofod Hanna - Submitted: 2026-04-17 - Description: Is your data AI ready? Are your "consumers" ready for it? Don't let AI solely write your instructions, documentation and verified answers. You need a documentation system and process to steer the process. See the guide for links to notebooks, scripts and skills that take you further! My new favorite Tabular Editor C# Macro is on slide 5 😍 I'm happy to see that if you want to succeed with Chat with your data, optimizing and documenting semantic models are still (if not more) important. - Tags: data-agent, prep-for-ai, ai-ready-data, semantic-model - Contributor: Sandeep Pawar ### Conversational Analytics using Microsoft Fabric Data Agents(e2e tutorial) - LinkedIn URL: https://www.linkedin.com/posts/harsha-guggilla-221890b6_microsoftfabric-fabricdataagents-powerbi-activity-7424496964723179521-Sj0q - Author: Harsha Guggilla - Submitted: 2026-03-16 - Description: This post explains how Microsoft Fabric Data Agents can help teams answer unexpected business questions in real time by turning natural business language into trusted, governed analytical answers. It highlights the common pressure data teams face in review meetings when metrics suddenly shift and shows how conversational analytics can work effectively only when built on approved data, definitions and guardrails. - Tags: microsoftfabric, fabricdataagents, powerbi, dataengineering, analyticsengineering, genai, conversationalanalytics - Contributor: Harsha Guggilla ### Copilot vs Data Agents - LinkedIn URL: https://www.linkedin.com/posts/nadim-abou-khalil_agent-v-copilot-ugcPost-7439292923067707392-323-?utm_source=share&utm_medium=member_desktop&rcm=ACoAAACXVe0BAgnEWy4VG5-Uls4-c7M2P6w-pWQ - Author: Nadim Aboud-Khalil - Submitted: 2026-03-16 - Description: Microsoft Fabric now gives us Data Agents - purpose-built, grounded on your actual data sources (Lakehouse, Warehouse, SQL DB, KQL DB), and fully customizable with AI instructions, example SQL queries, and tone/format control. Compare that to the standalone Copilot: broad access, but limited customization and no instruction support. - Tags: copilot, dataagents - Contributor: Sandeep Pawar ### Data agent copilot studio experience - LinkedIn URL: https://www.linkedin.com/posts/hcruanes_we-just-launched-our-first-poc-of-a-data-share-7483040709349122049-eOG4/?utm_source=share&utm_medium=member_desktop&rcm=ACoAAACXVe0BAgnEWy4VG5-Uls4-c7M2P6w-pWQ - Author: View Héctor Cruañes’ profile Héctor Cruañes - Submitted: 2026-07-20 - Description: Author shared his experience using Fabric data agent in Copilot Studio. He liked how seamless it was but experienced high cap[acity utilization. - Tags: data-agent, copilot-studio, capacity - Contributor: Sandeep Pawar ### Data agent with SQL DB in Fabric - LinkedIn URL: https://www.linkedin.com/feed/update/urn:li:activity:7425691757016707072/ - Author: Sukhwant Kaur - Submitted: 2026-03-16 - Description: 🚀 You launched your first SQL database in Fabric? Wondering what else you can do next? Imagine being able to chat with your data—or empowering your whole team to interact with your database using natural language. That’s where Data Agents in Microsoft Fabric come in. Internet is buzzing with folks building Data Agents – Here’s your chance to to be part of the excitement. 👇 Check out my quick video to see what’s possible when you let Data Agents do the heavy lifting. Join the conversation, share what you build next, and let’s inspire each other to keep innovating! [hashtag#DataAgents](https://www.linkedin.com/search/results/all/?keywords=%23dataagents&origin=HASH_TAG_FROM_FEED) [hashtag#MicrosoftFabric](https://www.linkedin.com/search/results/all/?keywords=%23microsoftfabric&origin=HASH_TAG_FROM_FEED) [hashtag#LowCode](https://www.linkedin.com/search/results/all/?keywords=%23lowcode&origin=HASH_TAG_FROM_FEED) [hashtag#NoCode](https://www.linkedin.com/search/results/all/?keywords=%23nocode&origin=HASH_TAG_FROM_FEED) [hashtag#Innovation](https://www.linkedin.com/search/results/all/?keywords=%23innovation&origin=HASH_TAG_FROM_FEED) [hashtag#SQLdatabaseinFabric](https://www.linkedin.com/search/results/all/?keywords=%23sqldatabaseinfabric&origin=HASH_TAG_FROM_FEED) https://lnkd.in/eYwtMrNN - Tags: sqldb, dataagent - Contributor: Sandeep Pawar ### Data Agent to Data Memo - LinkedIn URL: https://www.linkedin.com/feed/update/urn:li:activity:7450982802990440448/ - Author: Sandeep Pawar - Submitted: 2026-04-18 - Description: Experimented with a pipeline to explore the data autonomously, find insights, find second order signals, create a cohesive narrative that's grounded in the data & context, added an optimization layer using [DSPy (Community)](https://www.linkedin.com/company/dspy/) to tune it and converted to speech. No external APIs, services, 100% in [hashtag#MicrosoftFabric](https://www.linkedin.com/search/results/all/?keywords=%23microsoftfabric&origin=HASH_TAG_FROM_FEED) . 🔊Listen, let me know. The novelty here is I used the recently published LLM-as-Verifier approach as a metric in GEPA to tune the narrative. (https://lnkd.in/g2Huycw9) - Tags: data-agent, ai, narration, tts - Contributor: Sandeep Pawar ### Data Agents with Business Central Data - LinkedIn URL: https://www.linkedin.com/feed/update/urn:li:activity:7407748417759891457/ - Author: Bert Verbeek - Submitted: 2026-03-16 - Description: Ever wished you could ask natural language questions about your Business Central data and get instant insights? With the new Data Agent inside Microsoft Fabric, that’s now possible! In my latest blog, I dive into: ✅ How Data Agent connects to Business Central ✅ Why this is a game-changer for self-service analytics ✅ Practical examples of asking questions on your ERP data If you’re working with Microsoft Fabric and Business Central, this is a must-read! - Tags: dataagent, businesscentral - Contributor: Sandeep Pawar ### Fabric Ontology with Data Agent - LinkedIn URL: https://www.linkedin.com/posts/activity-7449520968563048448-axF6?utm_source=share&utm_medium=member_desktop&rcm=ACoAAACXVe0BAgnEWy4VG5-Uls4-c7M2P6w-pWQ - Author: Chris Chalmers - Submitted: 2026-04-14 - Description: AI built my Fabric Ontology demo in under an hour! Thanks to GitHub Copilot, I have notebooks for loading Lakehouse tables with demo data, building a Fabric Ontology, and creating instructions for a Fabric Data Agent to query the whole thing. Visit my GitHub repo to see the prompts I used, how Ontology Playground helped, and the skills files that were created along the way. ![Image](https://github.com/user-attachments/assets/22057c41-b456-4c48-a8c5-d778e945f599) - Tags: data-agent, iq, ontology - Contributor: Sandeep Pawar ### From API to AI Agent: Turning Raw Data into Conversational Intelligence with Microsoft Fabric - LinkedIn URL: https://www.linkedin.com/pulse/from-api-ai-agent-turning-raw-data-conversational-fabric-al-qinneh-fifse - Author: Mohammad Al-Qinneh - Submitted: 2026-03-11 - Description: Data agent on top of Oura health data to chat with your own health data - Tags: data-agent, api, fabric - Contributor: Sandeep Pawar ### From Power BI to Conversational AI: Building Data Agents That Scales - LinkedIn URL: https://www.linkedin.com/feed/update/urn:li:activity:7438277125381574657/?originTrackingId=BsideySFA5tcvClp69bQfQ%3D%3D - Author: Khaled Chowdhury - Submitted: 2026-03-16 - Description: Khaled will be presenting at SQL Saturday ATL on data agents - Tags: dataagent, introduction - Contributor: Sandeep Pawar ### How to build an AI agent in Fabric and Foundry to leverage your business data - LinkedIn URL: https://www.linkedin.com/posts/arash-besadi-aaa328169_fabric-fabricdataagent-foundry-ugcPost-7404865389605568512-XxA_?utm_source=social_share_send&utm_medium=member_desktop_web&rcm=ACoAAACXVe0BAgnEWy4VG5-Uls4-c7M2P6w-pWQ - Author: Arash Besadi - Submitted: 2026-03-16 - Description: If you have been waiting for a step‑by‑step tutorial to make an AI agent that “speaks” the language of your business data, this guide is for you. In this article I will show you how to: (1) build a Fabric Data Agent over your Fabric Lakehouse and (2) connect that agent to Microsoft Foundry to enable extended agent capabilities. - Tags: foundry, dataagent, stepbystep, lakehouse - Contributor: Sandeep Pawar ### Making Data AI-Ready with Intelligent Data Agents - LinkedIn URL: https://www.linkedin.com/pulse/making-data-ai-ready-intelligent-agents-pablo-junco-boquer-qo0fe/ - Author: Pablo Junco Boquer - Submitted: 2026-10-01 - Description: After several days at [FABCON & SQLCON - The Microsoft Fabric & SQL Community Conferences](https://www.linkedin.com/company/microsoft-fabric-community-conference/) in Barcelona, one of the evolutions that caught my attention was what is happening with Data Agents in [Microsoft Fabric](https://www.linkedin.com/showcase/microsoftfabric/) . It could be summarized as From talking to data to understanding the business I am calling this evolution Intelligent Data Agents 2.0. - Tags: data-agent, fabcon - Contributor: Sandeep Pawar ### Microsoft Fabric Data Agent Governance: From POC to Production - LinkedIn URL: https://www.linkedin.com/pulse/microsoft-fabric-data-agent-security-what-actually-your-srivastava-wuvff/ - Author: Hardik Srivastava - Submitted: 2026-11-05 - Description: This is Part 1 of series where we discussed on "RLS, CLS, OLS, identity, permissions, and why prompt instructions should never become your security boundary". - Tags: data-agent, security, fabric - Contributor: Hardik Srivastava ### Multi-agent routing for Fabric Data Agents using Microsoft Foundry - LinkedIn URL: https://www.linkedin.com/feed/update/urn:li:activity:7421334695377879040/ - Author: Mathias Halkjær - Submitted: 2026-03-16 - Description: Creating multi-agent architecture with data agent and Microsoft Foundry - Tags: foundry, dataagent, multi-agent, advanced - Contributor: Sandeep Pawar ### Production-Ready Microsoft Fabric Data Agents: A Practical Evaluation Workflow - LinkedIn URL: https://www.linkedin.com/posts/harsha-guggilla-221890b6_microsoftfabric-fabricdataagents-conversationalanalytics-activity-7425357574436257792-NcsX - Author: Harsha Guggilla - Submitted: 2026-03-16 - Description: This post explains why evaluating Microsoft Fabric Data Agents is essential before trusting them in production. It highlights that while these agents can reduce response time and ease pressure on data teams, their real value depends on whether their answers are accurate, consistent, and grounded in approved business logic. - Tags: microsoftfabrichashtafabricdataagents, conversationalanalytics, dataengineering, analyticsengineering, microsoftpowerbi, enterpriseanalytics, mlops, llmops, aievaluation, moderndatastack - Contributor: Harsha Guggilla ### The Fabric Data Agent Routing Challenge and the Architecture That Solved It - LinkedIn URL: https://www.linkedin.com/pulse/fabric-data-agent-routing-challenge-architecture-solved-dagdelen-xob4f/ - Author: Fatih Dagdelen - Submitted: 2026-07-20 - Description: We recently encountered an important architectural constraint while integrating Microsoft Fabric Data Agent with Microsoft Copilot Studio. Our use case was straightforward: Business users needed to ask questions about supplier, procurement, invoice, and spend data. At the same time, they also needed to trigger operational processes such as supplier onboarding, purchase approvals, support requests, and data issue reporting. The post shows how to separate analytical vs operational flow in Copilot studio. - Tags: data-agent, copilot-studio, instructions, multi-agent, routing - Contributor: Sandeep Pawar ### What We Learned Building a Real-World Fabric Data Agent — The Honest Field Notes - LinkedIn URL: https://www.linkedin.com/pulse/what-we-learned-building-real-world-fabric-data-agent-ankit-kumar-ass9e/ - Author: Ankit Kumar - Submitted: 2026-03-26 - Description: 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. - Tags: data-agent, semanticmodel, tips, iq, ontologies, lakehouse, limitations, gql, sql - Contributor: Sandeep Pawar --- ## Learning Paths ### Build Your First Data Agent - Page: https://fabricdataagent.com/learn/build-your-first-agent/ - Difficulty: intermediate - Estimated Time: 5 hours - Description: A hands-on learning path that guides you through building a functional data agent from scratch. - Tags: hands-on, tutorial, intermediate - Contributor: Sandeep Pawar #### Learning Items - **Building Intelligent Data Agents with Fabric and Azure OpenAI** (article): Learn how to combine Fabric with Azure OpenAI for intelligent data agents. - /articles/ - **Advanced Data Agent Patterns and Architectures** (video): Deep dive into advanced patterns for building data agents. - /videos/ - **Semantic Link Labs** (tool): Use this toolkit for building semantic layers and connecting agents to data. - https://github.com/microsoft/semantic-link-labs - **Best Practices for Fabric Data Agent Development** (article): Learn production-ready patterns including error handling and performance optimization. - /articles/ ### Getting Started with Fabric Data Agents - Page: https://fabricdataagent.com/learn/get-started/ - Difficulty: beginner - Estimated Time: 3 hours - Description: Everything you need to know to get up and running with Microsoft Fabric Data Agents. Start here if you're new. - Tags: beginner, fundamentals, getting-started - Contributor: Sandeep Pawar #### Learning Items - **Get Started with Fabric Data Agent Documentation and Tutorial** (resource): Follow the official Microsoft tutorial to set up a data agent in Fabric using a lakehouse. Covers creating a data source, configuring the agent, and running your first queries. - https://learn.microsoft.com/en-us/fabric/data-science/data-agent-end-to-end-tutorial - **Prep Data for AI** (video): Learn about preparing your data and semantic models for use with data agents. Covers naming conventions, schema design, and the Prep for AI feature in Power BI. - https://www.youtube.com/live/IRYn_N0kKt4 - **Build Your First Data Agent** (video): A beginner-friendly walkthrough that takes you through the setup and configuration step by step, from creating your first agent to asking questions in natural language. - https://www.youtube.com/watch?v=ul16PjHNiVs - **Learn About Best Practices** (resource): Read the official best practices for configuring data agents. Covers agent-level instructions, data source selection, terminology, and query logic. Also see the semantic model best practices at https://learn.microsoft.com/en-us/fabric/data-science/semantic-model-best-practices. - https://learn.microsoft.com/en-us/fabric/data-science/data-agent-configuration-best-practices - **Share Your Data Agent Securely** (resource): Learn how to publish, version, and share your data agent with others. Covers publishing a read-only version, adding descriptions, and sharing via Microsoft 365 Copilot, Teams, or a custom app. - https://learn.microsoft.com/en-us/fabric/data-science/data-agent-sharing ### Production-Ready Agent Patterns - Page: https://fabricdataagent.com/learn/production-patterns/ - Difficulty: advanced - Estimated Time: 8 hours - Description: Advanced patterns and architectures for deploying data agents at scale in production environments. - Tags: advanced, production, architecture, patterns - Contributor: Sandeep Pawar #### Learning Items - **Best Practices for Fabric Data Agent Development** (article): Essential best practices for production deployments. - /articles/ - **Advanced Data Agent Patterns and Architectures** (video): Multi-agent orchestration, RAG patterns, and real-time processing. - /videos/