Introducing Cube.
The first platform where AI builds your data model for you.
Get accurate answers, dashboards and reports automatically.
No hallucinations. All grounded in the semantic layer.
Cube is free to start at cube.dev
You can now run your analytics workflow in Cube directly from Snowflake CoCo, from importing your Snowflake metric definitions to building and managing dashboards and visualizations in Cube.
If your team already works in Snowflake CoCo, Cube can fit naturally into that workflow.
Five years ago, we introduced the first version of Cube Store, our query engine for building and serving pre-aggregations. It is a key component of how Cube builds smaller aggregated tables from semantic layer definitions and uses aggregate awareness to route queries to matching
About a year ago, we shifted Cube's focus from the universal semantic layer to agentic analytics.
The semantic layer is the key foundation for agentic analytics, and we had the best one on the market. But there was still a lot to build to properly use and query the semantic
5 things we learned from building an agentic analytics harness at Cube over the last 12 months.
A year ago, we refocused our product from bringing consistent metrics to legacy BI tools toward agentic analytics. Legacy BI is dying and doesn’t need consistent metrics, but AI