Unity Catalog Pages are a human-curated layer in Databricks’ Genie Ontology that stores authoritative definitions of business terms, links them to catalog assets, and lets agents like Genie One ground answers in organization-approved meaning.
Pages provide a governed, single place to capture authoritative definitions (terms, entities, acronyms) alongside the data and assets they describe.
Genie Ontology uses Pages plus automatically learned knowledge (dashboards, queries, tables) so agents can retrieve explicit definitions rather than guessing.
Domains, metric views, and certifications work with Pages to scope where agents look, how numbers are computed, and which assets to trust.
# Pages are
Unity Catalog Pages are a new, governed place to record the authoritative definitions your business relies on: key terms, entities, acronyms, and the context that explains how to use them. They live inside Unity Catalog Discover and are modeled as part of Databricks' Genie Ontology so AI agents have direct access to organization-approved meaning when answering questions.
# Why this matters
# Ontology
Together, these elements produce a single, governed picture of the business that agents can rely on.
# Page structure and capabilities
Each Page combines structured fields and a rich content area. Structured fields include owner, synonyms, and a description. The Page body can contain links, images, tables, and inline references to Unity Catalog and workspace objects. Key features:
# Pages
# How agents use Pages in practice
# Governance and traceability
Because Pages are governed Unity Catalog objects, they carry ownership and can be certified or deprecated like other catalog assets. Grounding decisions are visible: agents cite Pages they used, and users can inspect the definition and ownership before acting on results.
# What teams will gain
Teams get a single, discoverable place for authoritative business meaning, linked directly to the assets that implement it. That reduces ambiguity, improves reproducibility of analytics, and makes AI-driven answers easier to verify.
# Short example
Define "active customer" on a Page with owner, synonyms, description, related table, and source links. An agent answering a question about churn can fetch that Page, compute metrics using the referenced table and metric views, and show the Page as a clickable source so the analyst can confirm the definition used.
Unity catalog managed tables allow you to control the placement of your data when...
Retrieval-augmented generation has become a standard pattern for grounding large language models in enterprise data. A typical implementation converts documents into embeddings, stores them in a vector database, retrieves the most similar chunks for a query, and adds those chunks to the model prompt. This works well fo
Your next campaign launch does not have to stall on the landing page. You describe it the way you would brief an agency (audience, goal, story, call to action), and minutes later a production-ready page sits in your own Drupal site, built only from your organization's approved components, on brand and accessible from t
Open WebUI is a universal chat interface with connectivity to local or remote LLM providers, custom files, documents, and a knowledge base, with full customization of model capabilities. Application features are configured both personally for a user account and globally by admin users. This article continues the explor
In our previous posts, we showed how open table formats, open APIs and unified governance...
At Data and AI Summit, we announced the evolution of Genie Spaces to Genie Agents,...
Loading more related stories...
Open the app view to save this story, compare related coverage, and continue from the same source.