Microsoft Fabric Data Agent

What is Microsoft Fabric Data Agent?

Fabric data agent is a generally-available feature inside Microsoft Fabric that lets anyone ask plain-English questions over an organization's own lakehouse, warehouse, Power BI and Eventhouse data and get back a governed, read-only answer — no SQL, DAX or KQL required. Configured similarly to publishing a Power BI report, it runs on Azure OpenAI's Assistant APIs, translating each question into the right query language for whichever connected source actually holds the answer, then enforces the requesting user's own permissions and any Microsoft Purview governance policy before returning a result. It ships as part of an existing Fabric or Power BI Premium capacity, not as a separate product.

What does Microsoft Fabric Data Agent do?

An admin selects up to five data sources — any mix of lakehouses, warehouses, Power BI semantic models, KQL/Eventhouse databases, ontologies or Microsoft Graph — picks the specific tables each should expose, then adds written instructions and up to 100 example question/query pairs per source to steer the agent toward the organization's own vocabulary. Once published, a user's question is parsed against Fabric's own responsible-AI and Purview policies, routed to whichever source appears to hold the answer, and converted into a live NL2SQL, NL2DAX, NL2KQL or Graph query — read-only, and scoped to exactly the data that requesting user's own credentials and Row-/Column-Level Security already allow. Results come back capped at 25 rows and 25 columns, designed for a conversational insight rather than a full data export. A data agent can be queried from the Fabric portal itself, Microsoft 365 Copilot, Copilot Studio, Azure AI Foundry or Microsoft Teams, and — since a public REST API and Python SDK shipped — from a developer's own code, pipeline, or external multi-agent orchestrator via an OpenAI-compatible runtime endpoint. Git integration and deployment pipelines let a configuration be version-controlled and promoted from dev to production like any other software artifact.

Key features

• Multi-source natural-language query routing: Combines up to 5 sources per agent (lakehouse, warehouse, Power BI semantic model, KQL/Eventhouse, ontology, Microsoft Graph) and routes each question to the right generator — NL2SQL, NL2DAX, NL2KQL, or a Graph query.
• Inherited governance, not bolted on: Every query runs using the requesting user's own credentials, respects Power BI Row-/Column-Level Security, and is subject to Microsoft Purview DLP and access-restriction policies automatically.
• Configurable via instructions + example queries: Up to 100 example question/query pairs per source, plus free-text instructions, steer the agent toward an organization's own vocabulary and preferred source for a topic.
• Public REST API, Python SDK and MCP-style runtime endpoint: A public management-plane API and Python SDK (made generally available in 2026) let developers create, configure and publish data agents in code; a runtime OpenAI-compatible endpoint and MCP-based invocation from Copilot Studio/Azure AI Foundry open it to external orchestrators.
• Git-backed ALM: Data agent configurations can be version-controlled via Git integration and promoted dev-to-production through Fabric deployment pipelines, with built-in diagnostics for troubleshooting query generation.

What are Microsoft Fabric Data Agent's use cases?

• Self-serve BI Q&A: A regional sales manager asks "which products underperformed in EMEA last quarter?" in plain English and gets a governed answer pulled live from the warehouse, without filing a ticket with the data team.
• Embedding governed data access into a larger agent: A platform team building a multi-agent system in Azure AI Foundry adds the company's Fabric data agent as a tool, so any orchestrated agent can pull governed financial or operational data without a separate, ungoverned integration.
• Programmatic querying via the public API: A developer uses the Fabric data agent Python SDK to create and publish a new agent as part of a CI/CD pipeline, rather than clicking through the Fabric portal by hand.

What does Microsoft Fabric Data Agent integrate with?

• Lakehouses, Warehouses, Power BI semantic models, KQL/Eventhouse databases, ontologies, Microsoft Graph (up to 5 combined per agent)
• Microsoft 365 Copilot, Copilot Studio, Azure AI Foundry, Microsoft Teams
• Microsoft Purview (DLP, access-restriction policies, audit/eDiscovery)
• Public REST API + Python SDK (management plane); OpenAI-compatible runtime endpoint

Why use Microsoft Fabric Data Agent?

• Governance is inherited from the platform itself — every query runs on the requesting user's own credentials and is automatically subject to Power BI Row-/Column-Level Security plus Microsoft Purview DLP and access-restriction policies, not a separate permissions layer bolted on top.
• Purpose-built query generation per source type (NL2SQL, NL2DAX, NL2KQL, and Microsoft Graph queries) rather than one generic text-to-SQL layer, letting a single agent span up to 5 combined structured sources.
• A public REST API and Python SDK went generally available in 2026, alongside an OpenAI-compatible runtime endpoint and MCP-based invocation from Copilot Studio and Azure AI Foundry — real programmatic and multi-agent embedding, not just a portal chatbot.
• No separate product to buy or license — it ships inside Fabric/Power BI Premium capacity you may already own, with Git-backed ALM (version control, deployment pipelines, diagnostics) for treating a data agent's configuration like real software.

Pros & cons

Microsoft Fabric Data Agent pricing

• Fabric F2 capacity (minimum required)~$0.36/hr / pay-as-you-go (~$263/mo always-on); ~$156/mo on a 1-year reserved commitment — third-party estimate, since Azure's own calculator requires sign-in for a quote
• Power BI Premium P1+ (alternative path)Existing capacity

See current pricing on learn.microsoft.com ↗Compare Microsoft Fabric Data Agent alternatives →

Microsoft Fabric Data Agent review

Fabric data agent is the one listing in this index whose "agent" ships embedded inside a full enterprise data platform rather than as a standalone product to buy — and that changes what it's actually good at. Its real strength is governance you don't have to build yourself: every query runs on the requesting user's own credentials, respects Power BI Row-/Column-Level Security, and is automatically subject to Microsoft Purview DLP and access-restriction policies, while purpose-built NL2SQL/NL2DAX/NL2KQL routing lets one configured agent span up to five structured sources at once. A public REST API, Python SDK and MCP-based invocation from Copilot Studio and Azure AI Foundry — all made generally available in 2026 — mean it's no longer just a Fabric-portal chatbot; it can be a governed data tool inside a larger multi-agent system. The honest limits are real, though: you cannot change or fine-tune the underlying model, it only reads structured data (no PDFs, no non-English questions), responses are capped at 25 rows and 25 columns, and there is no way to try it without an existing paid Fabric or Power BI Premium capacity — independent estimates put the minimum entry (an always-on F2) at roughly $263/month regardless of whether the data agent itself is ever queried. Pick it if your organization already runs on Fabric or Power BI Premium and wants a governed, natural-language layer over that data without buying a separate product; look elsewhere (or at a general enterprise search platform like Glean) if you need to search unstructured documents, swap models, or don't already have Fabric capacity to run it on.

The one listing in this index whose agent ships embedded inside a full enterprise data platform — governance (permissions, DLP, row/column security) is inherited from Fabric itself, not a separate layer to configure.

Frequently asked questions