Business users self-serve in natural language, analysts go faster, and every answer stays grounded in the governed semantic layer — for your team and your customers.
Just like these companies:
Agentic, not text-to-SQL
The agent reasons over modeled metrics, dimensions, and joins — picking the right fields instead of guessing at a schema.
Break a number down, change the grain, slice by a new dimension — the kind of moves an analyst makes by hand, run for you.
Ask the next question and the agent carries the prior filters, time range, and definitions forward across the thread.
Grounded in the model
Governed definitions stay fixed. Revenue means the same thing in every exploration, for every user — that's what free-form text-to-SQL can't promise.
The agent builds new calculations and views on top of the model without redefining what's underneath — flexibility and governance at the same time.
Access rules live in the model and apply on every query — for your own team and for end users in embedded analytics.
Business users and analysts
Ask in plain language and get a governed answer back — no SQL, no waiting on the data team's queue.
Power users skip the boilerplate and pick up where the agent left off — the question is already framed against the model.
When an exploration needs to go further, drop into Semantic SQL or open a workbook — same governed definitions underneath.
Wherever you work
Analytics Chat, workbooks, and dashboards — explore, build, and publish without leaving the platform.
Query the governed model from Claude, ChatGPT, or an agent you build, each connected over MCP.
Drop the Slack Agent into a thread and follow up where your team already talks — permissions carry through.
Why it works
More than 400 companies ground their exploration on Cube's governed model, so answers stay consistent and scoped to each user — your team and your customers alike. Brex chose Cube over the dbt Semantic Layer and LookML.
The semantic layer is what makes the AI useful.
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