GooglefeatureSemantic Model Support in Knowledge Catalog (Generally Available)
Google Cloud's Knowledge Catalog can now pull in metric and business definitions from Looker, dbt, Snowflake, Databricks, and SAP, so agents answer with the same numbers your reports use.
Details
- Knowledge Catalog now reads in metric definitions you have already built elsewhere: Looker LookML, BigQuery Graph, dbt MetricFlow, Snowflake Semantic Views, Databricks Metric Views, and SAP Business Data Cloud.
- Those definitions are linked into one map of your data that Gemini and custom agents use as their reference when answering.
- Knowledge Studio, in preview, lets you browse that map and package checked assets into sets agents can use.
- Google says grounding agents this way made them nearly 4x more accurate in its internal tests, with fewer tokens used.
Best for
Making sure an AI agent calculates revenue, ROAS, or conversion the same way your dashboards already do.
When to use it
Agents asked data questions give numbers that do not match the official reports.
Who benefits
Analytics and marketing ops teams on Google Cloud whose metrics are defined in Looker, dbt, or a warehouse.
Join the newsletter to get ahead with AI.
I share strategies, new modules, free guides, and tools to get you better at using AI in your work.
Leading a team? See team programs →