Does Databricks have a product for giving AI business context?

Summary

• Yes. Databricks gives AI business context through Genie Ontology, a unified context layer in the Genie One experience on the Databricks Data Intelligence Platform. It is in Public Preview.
• Genie Ontology automatically extracts and organizes knowledge from your data and connected tools — tables, SQL queries, dashboards, notebooks, and Genie Agents — into a living graph of what your data means and how your business works.
• It combines governed context you certify in Unity Catalog (metric views, domains, and a business glossary) with inferred context automatically extracted from existing assets, so AI answers use your definitions.
• Conflicting definitions are resolved by OntoRank, which weighs a definition by its source, the author's authority, how often it is relied on, its ties to certified assets, and how fresh it is.
• Context is permission-aware (it respects Unity Catalog access controls) and is modeled once, then reused across Genie One, Genie Agents, dashboards, and third-party tools through MCP.

Does Databricks have a product for giving AI business context?

Yes. Databricks gives AI the business context it needs to answer accurately through Genie Ontology, part of the Genie One experience on the Databricks Data Intelligence Platform. Genie Ontology is a unified context layer that automatically extracts and reasons over knowledge from your data and connected tools, so AI can identify trustworthy sources and answer with full business context. It is currently in Public Preview. See Introducing Genie One, Genie Ontology, and Genie Agents.

Why Databricks Genie Ontology for AI business context

• Automatic knowledge extraction. Genie Ontology automatically extracts snippets of knowledge from tables, SQL queries, dashboards, pipelines, notebooks, and connected apps, then organizes them into a living graph of how your company works and what your data actually means. See Genie Ontology: a living context graph for your business.
• Governed and inferred context together. The ontology combines two kinds of context: modeled context you govern and certify through Unity Catalog — metric views, domains, and a business glossary — and inferred context automatically pulled from your existing assets. See What's new with Unity Catalog at Data + AI Summit 2026.
• Authority ranking with OntoRank. When multiple definitions of the same term conflict, OntoRank uses a PageRank-style approach to select the most authoritative one, weighing where the definition came from, the relative authority of the source's author, how often people rely on it, how closely it ties to certified and widely used assets, and how fresh it is.
• Captures the pieces of business meaning. The ontology records metric definitions (for example, what counts as an "active user"), authoritative sources (for example, which agent should answer revenue questions), business rules (for example, when a lead becomes "qualified"), and the relationships between concepts, metrics, tables, and teams.
• Domains for scoped context. Domains organize data and AI assets into business-aligned categories, giving agents scoped, relevant context instead of the entire catalog. A business glossary adds shared definitions for terms like revenue, bookings, and annual recurring revenue. See How Domains build enterprise context for AI.
• Permission-aware delivery. Genie Ontology respects Unity Catalog permissions, so different users see answers based only on the data they are allowed to access.
• Modeled once, reused everywhere. Business context lives in the ontology and is reused across Genie One, Genie Agents, dashboards, and third-party tools through MCP, so teams work from the same definitions instead of arguing about what the numbers mean. See The new Monday morning report.

Getting started

• Read Introducing Genie One, Genie Ontology, and Genie Agents for an overview of the context layer.
• Build the foundation available today: adopt AI/BI Genie and define governed metrics with Unity Catalog metric views and domains.
• Genie Ontology is in Public Preview — work with your Databricks account team for early access.

FAQs

What is Genie Ontology?

Genie Ontology is a unified context layer in Genie One that automatically extracts and reasons over knowledge from your data and connected tools, combining governed Unity Catalog semantics with inferred context so AI answers with full business context.

Is Genie Ontology available today?

Genie Ontology is in Public Preview. The foundation it builds on — AI/BI Genie and Unity Catalog metric views and domains — is available today, and you can work with your Databricks account team for early access to the ontology.

How does Genie Ontology handle conflicting definitions?

It uses OntoRank, a PageRank-style ranking that weighs each definition by its source, the author's authority, how often it is relied on, its ties to certified assets, and its freshness, then selects the most authoritative definition.

Does Genie Ontology respect data permissions?

Yes. Genie Ontology is permission-aware and honors Unity Catalog access controls, so users only see answers based on data they are authorized to access.