Cube

Key Features

• •Semantic Layer: Cube's semantic layer keeps definitions consistent across all surfaces—Analytics Chat, dashboards, and embedded analytics. It eliminates metric fragmentation by defining each metric once, ensuring every query returns the same answer regardless of the tool or user.
• •Analytics Chat: This natural-language interface allows users to ask questions in plain English. Cube builds queries against the semantic model, delivering accurate, governed results. It also supports agent-to-agent communication via MCP for advanced AI workflows.
• •Embedded Analytics Suite: Cube provides APIs, iframes, and Creator Mode for embedding AI-powered analytics into SaaS products. Multi-tenant by construction, it ensures governance flows from the model to each customer's permissions, with full branding customization.
• •Creator Mode: An embedded feature that lets end-users create and edit workbooks and dashboards directly inside the application. It empowers customers to build their own analytics experiences without leaving the host product, reducing support burdens.
• •Core Data APIs: These give developers maximum control at the data layer, enabling them to build any UI on top of Cube's governed data. This flexibility allows for bespoke analytics interfaces while maintaining consistent semantics.
• •Multi-Tenant Governance: Cube ensures that data permissions and metric definitions are enforced per tenant. This built-in governance means that embedded analytics are both powerful and compliant, meeting the security needs of enterprise customers.

Use Cases

• •Embedded AI Financial Analyst: Brex built a customer-facing AI analyst using Cube's semantic layer. Their customers can ask complex financial questions and receive accurate, chart-embedded answers, improving trust and reducing support tickets.
• •Internal AI-Driven QBRs: Drata used Cube to power quarterly business reviews with natural-language queries. CSMs saved dozens of hours each quarter by asking questions in plain English and getting instant, governed insights from their data.
• •Transitioning from Dashboards to Dialogue: Alcon moved from static dashboards to dialog-driven analytics. Executives now type questions and receive contextualized answers with charts, making data exploration faster and more intuitive for non-technical users.
• •Customer-Facing Analytics Portal: Webflow integrated Cube Cloud with ClickHouse to deliver internal and external embedded analytics. Different teams accessed data without database complexity, enabling self-service analytics with consistent metric definitions.
• •Multi-Product Analytics for SaaS: Companies like Freshworks and Intuit use Cube to offer analytics across their product suites. The semantic layer ensures that customer-facing and internal reports match, reducing confusion and enhancing data-driven culture.

Who is this for?

Cube is designed for SaaS companies, data engineering teams, BI analysts, product managers, and executives who need to deliver consistent, governed analytics at scale. It serves organizations building both internal BI and customer-facing embedded analytics, especially those adopting AI agents for data querying. Healthcare, fintech, and enterprise software teams benefit from multi-tenant governance and customizable branding. Cube also targets data teams tired of reconciling inconsistent metrics across tools and seeking a unified semantic layer to power AI chat, dashboards, and reports.