Define your metrics, dimensions, joins, and access rules once in the semantic layer. Every consumer — internal BI, embedded analytics, and AI agents — reasons over the same governed model and returns the same trustworthy numbers.
Just like these companies:
Define once
Revenue, churn, active users — defined once in the model instead of re-derived in every report, app, and query.
Internal BI, embedded analytics, and AI agents all read the same definitions, so the number is the same wherever it shows up.
Edit a definition once and every consumer picks it up — no chasing down divergent copies of the same metric.
Model in code or visually
Define metrics, dimensions, and joins in YAML, JavaScript, or Python — version-controlled and reviewed like the rest of your stack.
Build and edit the same model in the Visual Model Editor, so analysts and data engineers can collaborate on one source of truth.
Work in the Data Model IDE, iterate in the Playground, and test changes in dev mode before they reach production.
Governed and multi-warehouse
Row-level and column-level access rules live in the semantic layer, scoped to each user and role.
The same rules apply whether the query comes from a dashboard, an embedded app, or an AI agent — there's no back door around the model.
Cube sits on top of Snowflake, BigQuery, Redshift, and Databricks — it governs your data where it already lives, it doesn't replace it.
dbt-friendly, AI-grounded
Cube reads your existing dbt models, so the metrics you've already defined become governed, reusable definitions.
Agents reason over governed definitions instead of guessing against raw tables — which is why the answers hold up.
Pre-aggregations and APIs let agents and embedded apps query the governed model quickly, without losing consistency.
Why a semantic layer
Brex chose Cube over the dbt Semantic Layer and LookML — the semantic layer is what makes the AI useful at scale.
The future of reporting isn't a chart, it's an insight. Large language models are becoming a commodity — the LLM is the engine, but the semantic layer is the map. A well-modeled ontology is the difference between 'I don't understand that question' and a correct, contextualized answer with a chart and a clear explanation. Cube gives us the foundation to make that real for every customer.Dan MeshkovStaff Software Engineer, BrexRead the Story
Cube becomes our single source of truth for metric definitions and powers everything from customer-facing dashboards to AI-driven quarterly business reviews. CSMs gain back dozens of hours each quarter, enabled by Cube’s semantic layer and agentic analytics.
Anthony Cronander
Senior Analytics Engineer, Drata
We integrated Cube Cloud smoothly with ClickHouse, leveraging both for fast query execution while maintaining the abstraction needed for different teams to access data without diving into database-specific complexities.
Rocio Delgado
Senior Engineering Manager at Webflow
Without Cube, our data analysts might have to write 20 different queries for a single core business metric. With Cube, that metric is defined once in the data model, and every downstream tool uses that definition along with the associated calculation logic.
Dr. Jun Huang
Global Head of Data Science at Alcon
See how Cube can help you get the most of your data