fabric-data-agent

Automate Microsoft Fabric Data Agent provisioning via REST API or PowerShell.

16|1|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/PatrickGallucci/fabric-skills --skill fabric-data-agent-patrickgallucci
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fabric-data-agent
Source: https://github.com/PatrickGallucci/fabric-skills/tree/main/skills/fabric-data-agent
Command: npx skills add https://github.com/PatrickGallucci/fabric-skills --skill fabric-data-agent-patrickgallucci

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Az.Accounts, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Create, configure, and manage Microsoft Fabric Data Agents that enable natural language Q&A over lakehouses, warehouses, Power BI semantic models, KQL databases, and ontologies. Use when asked to build data agents, configure NL2SQL/NL2DAX/NL2KQL experiences, write agent instructions, create example queries, automate data agent provisioning via REST API or PowerShell, integrate Fabric data agents with Azure AI Foundry, or troubleshoot data agent configuration issues.

Core Features & Use Cases

  • Create and configure Fabric Data Agents to enable NL2SQL, NL2DAX, and NL2KQL across multiple data sources
  • Automate provisioning and management via REST API or PowerShell, including publishing and versioning
  • Write agent and data-source instructions, add example queries, and integrate with Azure AI Foundry
  • Manage the Operations Agent definition (Configurations.json) and enable end-to-end data querying workflows
  • Troubleshoot configuration issues and optimize data-source access and security
  • Use Case: Publish a data agent in Fabric, connect to a lakehouse, and answer natural-language questions with generated SQL/DAX/KQL

Quick Start

Install the skill by copying it into your Fabric workspace and then create a Data Agent in the Fabric portal to configure sources, instructions, and examples.

Frequently Asked Questions about fabric-data-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure a Fabric Data Agent for natural language querying over a lakehouse?

To configure a Fabric Data Agent for natural language querying, you provision the agent in the Fabric portal, connect it to your lakehouse or warehouse, add data sources, write agent instructions, and define example queries to enable NL2SQL or NL2DAX capabilities.

Can I automate Microsoft Fabric Data Agent provisioning using PowerShell and the REST API?

Yes, you can automate Microsoft Fabric Data Agent provisioning using PowerShell and the REST API to create, configure, publish, and manage agents programmatically, including managing the Operations Agent definition and versioning.

Does Azure AI Foundry integrate with Fabric Data Agents for end-to-end querying?

Azure AI Foundry integrates with Fabric Data Agents to enable end-to-end natural language querying workflows, allowing you to connect configured agents to Foundry for generating SQL, DAX, or KQL from user questions.

What is the best way to write instructions and examples for NL2SQL and NL2DAX data agents?

The best way to write instructions for NL2SQL and NL2DAX data agents is to define clear operational guidelines in the agent configuration, provide specific example queries, and follow instruction best practices to optimize natural language translation accuracy.

Do I need the Az.Accounts PowerShell module to manage Fabric Data Agents?

Yes, you need the Az.Accounts PowerShell module to authenticate and manage Fabric Data Agents when automating provisioning, configuration, and operational workflows via PowerShell scripts.

Why is my Fabric Data Agent not returning accurate results for natural language questions?

Inaccurate Fabric Data Agent results often stem from poorly defined agent instructions, insufficient example queries, or incorrect data-source configurations, requiring troubleshooting of the Configurations.json file and optimization of data-source access.