Databricks makes Genie Ontology generally available
The 1.6× accuracy gain at under half the tokens suggests ontology grounding may matter more to agent reliability than model choice itself. Enterprise teams already running Unity Catalog can layer this on without new governance plumbing, making it a practical test case for agent accuracy work. Power BI and Google Drive connectors put it in direct competition with Microsoft's Fabric knowledge tooling.
Databricks has announced the general availability of Genie Ontology, a layer that formally models business knowledge so its Genie agents can answer with trusted, governed information. According to Databricks, a benchmark developed with Turing (turingcom) shows Genie with Genie Ontology delivers 1.6× the accuracy while using less than half the tokens.
Most business knowledge is not formally modeled; it sits in dashboards, SQL queries, notebooks and documents. Genie Ontology learns from everyday work, combines that context with Unity Catalog semantics, and ranks sources by authority so agents rely on trusted information. The GA release adds Genie Search across Google Drive, Jira, Confluence and Workday, external knowledge sources in Beta including Power BI business logic, and organizational directories covering people, teams and reporting relationships. Unity Catalog Domains and Pages also reach GA, with an Ontology Manager in Beta coming for curation and governance.
The release positions Databricks against enterprise knowledge-graph and agent-grounding offerings by building directly on its existing Unity Catalog governance layer, letting enterprises reuse semantic definitions they already maintain rather than rebuilding them for agents.
Genie Ontology is now Generally Available.
Most business knowledge isn't formally modeled. It lives in dashboards, SQL queries, notebooks and documents. Genie Ontology learns from everyday work, combines that context with governed Unity Catalog semantics, and ranks sources by authority so agents use trusted information.
What's new: - 𝗚𝗲𝗻𝗶𝗲 𝗦𝗲𝗮𝗿𝗰𝗵: Search enterprise knowledge across Google Drive, Jira, Confluence and Workday - 𝗘𝘅𝘁𝗲𝗿𝗻𝗮𝗹 𝗸𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝘀𝗼𝘂𝗿𝗰𝗲𝘀 (Beta): Bring in business logic from Power BI - 𝗢𝗿𝗴𝗮𝗻𝗶𝘇𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗱𝗶𝗿𝗲𝗰𝘁𝗼𝗿𝗶𝗲𝘀: Add people, teams and reporting relationships - 𝗨𝗻𝗶𝘁𝘆 𝗖𝗮𝘁𝗮𝗹𝗼𝗴 𝗗𝗼𝗺𝗮𝗶𝗻𝘀 𝗮𝗻𝗱 𝗣𝗮𝗴𝗲𝘀: Now GA - 𝗢𝗻𝘁𝗼𝗹𝗼𝗴𝘆 𝗠𝗮𝗻𝗮𝗴𝗲𝗿: Coming soon in Beta for curation and governance
In a benchmark developed with @turingcom, Genie with Genie Ontology delivers 1.6× the accuracy with less than half the tokens.
https://t.co/ro8weeDniF
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Databricks, Genie Ontology, Unity Catalog, agents.
Source attribution: curated from Databricks (@databricks). Cross-source corroboration: 2 independent sources have covered this development (including 宝玉), confirming industry-wide signal strength.
- 宝玉11-10 17:53Source
