Cube, the enterprise helping companies manage and optimize their analytics workflows, is debuting new intelligence capabilities that enable enterprises to develop AI and embedded analytics solutions with ease. These new features—AI API and chart prototyping for Cube Cloud—empower Cube customers to leverage the company’s universal semantic layer to streamline AI and embedded analytics solutions development while improving the quality of generative AI (GenAI).
Cube’s universal semantic layer—Cube Cloud—acts as the foundation for driving a unified understanding across the enterprise. It is an independent—yet interoperable—part of the modern data stack that sits between data sources and data consumers, enabling BI tools, embedded analytics, or AI agents and chatbots to work with the same semantics and underlying data—increasing overall trust, according to Cube.
Trust is key for GenAI implementation, as GenAI necessitates a robust understanding between entities and relationships to avoid hallucinations. Cube’s universal semantic layer brings the context that large language models (LLMs) need to produce accurate, meaningful outputs.
Cube’s AI API eliminates the need to create complex integrations between LLMs and Cube Cloud, streamlining the development of AI agents and chatbots. This ultimately drives the democratization of AI to any user, lowering the barrier of entry to understand company data via natural language, according to Cube.
“Customers like Spyne and Quantatec are already benefiting from the context provided by a universal semantic layer,” said Artyom Keydunov, co-founder and CEO of Cube. “Knowing the importance of the universal semantic layer to accurate LLM outputs, we were inspired by these customer use cases to simplify and accelerate development with the AI API. Now, Cube provides a standard interface for interacting with OpenAI as a turnkey solution for text-to-semantic layer queries.”
For embedded analytics, Cube Cloud’s new chart prototyping capability enables users to produce front-end TypeScript code from Playground 2.0, increasing time-to-market. These charts can be previewed before being embedded, paired with the choice to integrate via native REST or GraphQL APIs.
To learn more about Cube, please visit https://cube.dev/.