fabric-data-agent
Skill17 starsChanged 9 months agoMITView on GitHub
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.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- microsoft/rayfintheir own version, first seen Oct 13, 2026
- kimtth/ms-fabric-skills-dev-startertheir own version, first seen May 18, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- microsoft/rayfin★ 646same name
- kimtth/ms-fabric-skills-dev-starter★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- fabric-data-agent-perf-remediateSkill
- fabric-data-agent-remediateSkill
- fabric-data-factory-perf-remediateSkill
- fabric-dataflows-perf-remediationSkill
- fabric-delta-spark-perfSkill
- fabric-iqSkill
- fabric-lakehouse-access-controlSkill
- fabric-lakehouse-perf-remediateSkill
- fabric-lakehouse-views-perf-remediateSkill
- fabric-network-remediateSkill
- fabric-notebook-perf-remediateSkill
- fabric-onelake-perf-remediateSkill
- fabric-pandas-perf-remediateSkill
- fabric-pbi-perf-remediateSkill
- fabric-pbi-security-remediateSkill
- fabric-performance-monitoringSkill
- fabric-pyspark-perf-remediateSkill
- fabric-rest-api-perf-remediateSkill
- fabric-rest-api-remediateSkill
- fabric-rti-perf-remediateSkill
- fabric-spark-compute-perf-remediateSkill
- fabric-spark-compute-remediateSkill
- fabric-spark-perf-remediateSkill
- fabric-udf-perf-remediateSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 12 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 39
Add up to 5 data sources from the OneLake catalog (any mix of Lakehouse, Warehouse, PBI Semantic Model, KQL DB, Ontology)
- Distinctive: line 41
Write agent instructions — see instruction-best-practices.md
- Distinctive: line 42
Add example queries for each data source — see example-query-guide.md
- Distinctive: line 43
Test the agent in the chat pane with representative questions
- Distinctive: line 50
Create the agent item using the Fabric Items API — run New-FabricDataAgent.ps1
- Distinctive: line 52
Update the item definition using the Update Item Definition API
- Distinctive: line 57
Create and publish the Fabric Data Agent in the Fabric portal
- Distinctive: line 58
Create a Foundry Agent in the Azure AI Foundry portal
- Distinctive: line 59
Add a Microsoft Fabric connection to your Foundry project
- Distinctive: line 60
Create the agent with the Fabric tool enabled — see foundry-integration.md
- Distinctive: line 61
Create a thread, add a user question, run the thread, and retrieve the response
- Distinctive: line 62
Update Foundry agent instructions to describe what data the Fabric tool can access
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Microsoft Fabric Data Agents
Build conversational AI experiences that let users ask questions in plain English against structured data in Microsoft Fabric. Fabric Data Agents translate natural language into SQL, DAX, or KQL queries, execute them securely under the caller's identity, and return data-driven answers.
When to Use This Skill
- Creating a new Fabric Data Agent from the portal or via REST API
- Configuring data sources (Lakehouse, Warehouse, Power BI Semantic Model, KQL Database, Ontology)
- Writing effective agent-level or data-source-level instructions
- Authoring example queries (few-shot examples) to improve NL2SQL/NL2DAX/NL2KQL accuracy
- Automating data agent provisioning with PowerShell and the Fabric REST API
- Integrating a published Fabric Data Agent with Azure AI Foundry agents
- Managing the Operations Agent definition (Configurations.json) programmatically
- Publishing, sharing, and versioning data agents
- remediate query generation, data source permissions, or tenant settings
Prerequisites
| Requirement | Details |
| Fabric capacity | Paid F2+ SKU, or Power BI Premium P1+ with Fabric enabled |
| Tenant settings | Fabric data agent, Cross-geo processing for AI, Cross-geo storing for AI all enabled |
| XMLA endpoints | Enabled if using Power BI Semantic Model data sources |
| Data source access | At least Read permission on target lakehouses, warehouses, semantic models, or KQL databases |
| PowerShell (automation) | PowerShell 7.4+, Az.Accounts module |
| Azure AI Foundry (integration) | Foundry Project endpoint, Fabric connection, model deployment |
Step-by-Step Workflows
Workflow 1: Create and Configure a Data Agent (Portal)
- Navigate to your workspace and select + New Item > Fabric data agent
- Provide a descriptive name for the agent
- Add up to 5 data sources from the OneLake catalog (any mix of Lakehouse, Warehouse, PBI Semantic Model, KQL DB, Ontology)
- Select/deselect tables in the Explorer pane to control what the AI can query
- Write agent instructions — see instruction-best-practices.md
- Add example queries for each data source — see example-query-guide.md
- Test the agent in the chat pane with representative questions
- Select Publish and provide a description
- Share the published version with colleagues via workspace permissions
Workflow 2: Automate Data Agent via REST API (PowerShell)
- Authenticate with
Connect-AzAccountand obtain an access token - Create the agent item using the Fabric Items API — run New-FabricDataAgent.ps1
- Configure the Operations Agent definition (Configurations.json) — see operations-agent-schema.md
- Update the item definition using the Update Item Definition API
- Validate deployment by listing items in the workspace
Workflow 3: Integrate with Azure AI Foundry
- Create and publish the Fabric Data Agent in the Fabric portal
- Create a Foundry Agent in the Azure AI Foundry portal
- Add a Microsoft Fabric connection to your Foundry project
- Create the agent with the Fabric tool enabled — see foundry-integration.md
- Create a thread, add a user question, run the thread, and retrieve the response
- Update Foundry agent instructions to describe what data the Fabric tool can access
remediate
| Symptom | Cause | Resolution |
| Data agent option not visible in New Item | Tenant setting disabled | Admin enables "Fabric data agent" in Tenant Settings |
| Agent can't see my tables | Tables not selected in Explorer | Check table checkboxes in the data source Explorer |
| Queries return permission errors | Insufficient data access | Grant at least Read on the underlying data source |
| Example queries show validation errors | SQL/KQL syntax invalid or schema mismatch | Validate queries against the actual table schema |
| Agent misinterprets domain terms | Missing definitions in instructions | Add term definitions in Agent Instructions (up to 15,000 chars) |
| Power BI semantic model won't add | XMLA endpoints disabled | Enable "Power BI semantic models via XMLA endpoints" tenant switch |
| Published agent not accessible to colleagues | Workspace permissions not granted | Share the workspace or agent item with appropriate roles |
References
- Instruction Best Practices — How to write effective agent and data-source instructions
- Example Query Guide — Authoring few-shot examples for NL2SQL/NL2DAX/NL2KQL
- Operations Agent Schema — REST API definition structure (Configurations.json)
- Foundry Integration — Connecting Fabric Data Agents with Azure AI Foundry
- Microsoft Learn: Create a Fabric data agent
- Microsoft Learn: Data agent configuration
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

