Officially

From the publisher, with its history intact.

Databricks databricks.com

Data Ontology defined: The context layer your AI agents are missing

Imported from official source

AI Classified by Officially

  • Enterprise data architecture has always assumed a knowledgeable human sits between the data and the decision, supplying the context a schema can't. AI agents remove that human, and the assumption breaks.
  • Semantic layers and knowledge graphs tried to solve this before and often became shelfware, because modeling an entire enterprise by hand can't keep pace with how fast a business changes.
  • The fix isn't a bigger documentation project. It's an ontology that governs the small set of concepts that can't be wrong and continuously learns the rest from how the organization already works, the model Databricks has built into Genie Ontology.

    • Ask five people at the same company what "revenue" means and there's a chance you'll get five different answers, each one correct within its own context and incompatible with the others. For as long as a human analyst has sat between that ambiguity and the final report, the ambiguity has been manageable. It's tribal knowledge: the kind of thing a good analyst just knows.

    AI agents don't know it. And that's the problem.

    Richard Tomlinson has spent his career thinking about the layer of enterprise data that never quite shows up in the schema. In this conversation, he walks through why that layer, the ontology, is suddenly the most important piece of infrastructure most companies haven't built yet, why the last generation of attempts to build it largely stalled, and what has to be true of an ontology for it to hold up once agents start relying on it.

    Why do AI agents need business context that a schema can't provide?

    What's the assumption about enterprise data that AI agents are quietly breaking?

    This is an extract. The publication continues at the source.

    Read the original at the source: https://www.databricks.com/blog/data-ontology-defined-context-layer-your-ai-agents-are-missing

    Officially imported this from Databricks’s own source and shows an extract. If you work there, claiming the profile and verifying the domain lets you choose to show the full text here.

    Provenance

    Organization
    Databricks — imported from official source
    Official source
    https://www.databricks.com/feed RSS
    Imported
    September 21, 2026 22:30
    Versions
    1 recorded
    Identity
    https://www.databricks.com/blog/data-ontology-defined-context-layer-your-ai-agents-are-...

    Officially records where a publication came from, not whether it is true. Imported records are reproduced from an organization's own official source.