fabric-data-agent

Name: fabric-data-agent
Author: PatrickGallucci

16stars1forks

How to install fabric-data-agent?

patrickgallucci/fabric-skills/fabric-data-agent

$npx -y skills add PatrickGallucci/fabric-skills --skill fabric-data-agent

Installs into the current project.

Summary

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 instructi

Files · 1

View on GitHub

SKILL.md

1	# Microsoft Fabric Data Agents
2
3	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.
4
5	## When to Use This Skill
6
7	- Creating a new Fabric Data Agent from the portal or via REST API
8	- Configuring data sources (Lakehouse, Warehouse, Power BI Semantic Model, KQL Database, Ontology)
9	- Writing effective agent-level or data-source-level instructions
10	- Authoring example queries (few-shot examples) to improve NL2SQL/NL2DAX/NL2KQL accuracy
11	- Automating data agent provisioning with PowerShell and the Fabric REST API
12	- Integrating a published Fabric Data Agent with Azure AI Foundry agents
13	- Managing the Operations Agent definition (Configurations.json) programmatically
14	- Publishing, sharing, and versioning data agents
15	- remediate query generation, data source permissions, or tenant settings
16
17	## Prerequisites
18
19	\| Requirement \| Details \|
20	\| ------------------------------ \| -------------------------------------------------------------------------------------------- \|
21	\| Fabric capacity \| Paid F2+ SKU, or Power BI Premium P1+ with Fabric enabled \|
22	\| Tenant settings \| Fabric data agent, Cross-geo processing for AI, Cross-geo storing for AI all enabled \|
23	\| XMLA endpoints \| Enabled if using Power BI Semantic Model data sources \|
24	\| Data source access \| At least Read permission on target lakehouses, warehouses, semantic models, or KQL databases \|
25	\| PowerShell (automation) \| PowerShell 7.4+, Az.Accounts module \|
26	\| Azure AI Foundry (integration) \| Foundry Project endpoint, Fabric connection, model deployment \|
27
28	## Step-by-Step Workflows
29
30	### Workflow 1: Create and Configure a Data Agent (Portal)
31
32	1. Navigate to your workspace and select + New Item > Fabric data agent
33	2. Provide a descriptive name for the agent
34	3. Add up to 5 data sources from the OneLake catalog (any mix of Lakehouse, Warehouse, PBI Semantic Model, KQL DB, Ontology)
35	4. Select/deselect tables in the Explorer pane to control what the AI can query
36	5. Write agent instructions — see [instruction-best-practices.md](./references/instruction-best-practices.md)
37	6. Add example queries for each data source — see [example-query-guide.md](./references/example-query-guide.md)
38	7. Test the agent in the chat pane with representative questions
39	8. Select Publish and provide a description
40	9. Share the published version with colleagues via workspace permissions
41
42	### Workflow 2: Automate Data Agent via REST API (PowerShell)
43
44	1. Authenticate with `Connect-AzAccount` and obtain an access token
45	2. Create the agent item using the Fabric Items API — run [New-FabricDataAgent.ps1](./scripts/New-FabricDataAgent.ps1)
46	3. Configure the Operations Agent definition (Configurations.json) — see [operations-agent-schema.md](./references/operations-agent-schema.md)
47	4. Update the item definition using the Update Item Definition API
48	5. Validate deployment by listing items in the workspace
49
50	### Workflow 3: Integrate with Azure AI Foundry
51
52	1. Create and publish the Fabric Data Agent in the Fabric portal
53	2. Create a Foundry Agent in the Azure AI Foundry portal
54	3. Add a Microsoft Fabric connection to your Foundry project
55	4. Create the agent with the Fabric tool enabled — see [foundry-integration.md](./references/foundry-integration.md)
56	5. Create a thread, add a user question, run the thread, and retrieve the response
57	6. Update Foundry agent instructions to describe what data the Fabric tool can access
58
59	## remediate
60
61	\| Symptom \| Cause \| Resolution \|
62	\| -------------------------------------------- \| ----------------------------------------- \| ------------------------------------------------------------------ \|
63	\| Data agent option not visible in New Item \| Tenant setting disabled \| Admin enables "Fabric data agent" in Tenant Settings \|

People who liked this also viewed

6 picks

Type

fabric-data-agent

16stars1forks

View on GitHub

How to install fabric-data-agent?

patrickgallucci/fabric-skills/fabric-data-agent

$npx -y skills add PatrickGallucci/fabric-skills --skill fabric-data-agent

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Microsoft Fabric Data Agents
2
3	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.
4
5	## When to Use This Skill
6
7	- Creating a new Fabric Data Agent from the portal or via REST API
8	- Configuring data sources (Lakehouse, Warehouse, Power BI Semantic Model, KQL Database, Ontology)
9	- Writing effective agent-level or data-source-level instructions
10	- Authoring example queries (few-shot examples) to improve NL2SQL/NL2DAX/NL2KQL accuracy
11	- Automating data agent provisioning with PowerShell and the Fabric REST API
12	- Integrating a published Fabric Data Agent with Azure AI Foundry agents
13	- Managing the Operations Agent definition (Configurations.json) programmatically
14	- Publishing, sharing, and versioning data agents
15	- remediate query generation, data source permissions, or tenant settings
16
17	## Prerequisites
18
19	\| Requirement \| Details \|
20	\| ------------------------------ \| -------------------------------------------------------------------------------------------- \|
21	\| Fabric capacity \| Paid F2+ SKU, or Power BI Premium P1+ with Fabric enabled \|
22	\| Tenant settings \| Fabric data agent, Cross-geo processing for AI, Cross-geo storing for AI all enabled \|
23	\| XMLA endpoints \| Enabled if using Power BI Semantic Model data sources \|
24	\| Data source access \| At least Read permission on target lakehouses, warehouses, semantic models, or KQL databases \|
25	\| PowerShell (automation) \| PowerShell 7.4+, Az.Accounts module \|
26	\| Azure AI Foundry (integration) \| Foundry Project endpoint, Fabric connection, model deployment \|
27
28	## Step-by-Step Workflows
29
30	### Workflow 1: Create and Configure a Data Agent (Portal)
31
32	1. Navigate to your workspace and select + New Item > Fabric data agent
33	2. Provide a descriptive name for the agent
34	3. Add up to 5 data sources from the OneLake catalog (any mix of Lakehouse, Warehouse, PBI Semantic Model, KQL DB, Ontology)
35	4. Select/deselect tables in the Explorer pane to control what the AI can query
36	5. Write agent instructions — see [instruction-best-practices.md](./references/instruction-best-practices.md)
37	6. Add example queries for each data source — see [example-query-guide.md](./references/example-query-guide.md)
38	7. Test the agent in the chat pane with representative questions
39	8. Select Publish and provide a description
40	9. Share the published version with colleagues via workspace permissions
41
42	### Workflow 2: Automate Data Agent via REST API (PowerShell)
43
44	1. Authenticate with `Connect-AzAccount` and obtain an access token
45	2. Create the agent item using the Fabric Items API — run [New-FabricDataAgent.ps1](./scripts/New-FabricDataAgent.ps1)
46	3. Configure the Operations Agent definition (Configurations.json) — see [operations-agent-schema.md](./references/operations-agent-schema.md)
47	4. Update the item definition using the Update Item Definition API
48	5. Validate deployment by listing items in the workspace
49
50	### Workflow 3: Integrate with Azure AI Foundry
51
52	1. Create and publish the Fabric Data Agent in the Fabric portal
53	2. Create a Foundry Agent in the Azure AI Foundry portal
54	3. Add a Microsoft Fabric connection to your Foundry project
55	4. Create the agent with the Fabric tool enabled — see [foundry-integration.md](./references/foundry-integration.md)
56	5. Create a thread, add a user question, run the thread, and retrieve the response
57	6. Update Foundry agent instructions to describe what data the Fabric tool can access
58
59	## remediate
60
61	\| Symptom \| Cause \| Resolution \|
62	\| -------------------------------------------- \| ----------------------------------------- \| ------------------------------------------------------------------ \|
63	\| Data agent option not visible in New Item \| Tenant setting disabled \| Admin enables "Fabric data agent" in Tenant Settings \|

People who liked this also viewed

6 picks

Type