May 2026 Summaries

Artyom's recent post delves into the importance of SQL as the communication protocol for a standalone semantic layer, addressing the challenge of SQL's bottom-up evaluation in contrast to the top-down context needed for proper aggregation in a semantic layer. To tackle this, a term rewrite system based on E-Graph theory was developed, which allows for the resolution of measures at the correct aggregation level regardless of query structure. Historically, semantic layers, introduced by tools like Business Objects and adopted by many BI tools, have served to standardize metric definitions, ensuring consistent data interpretation. The resurgence of this need is driven by AI agents that generate SQL queries, often without the ability to discern incorrect results due to the lack of contextual understanding. Semantic SQL, therefore, becomes crucial in providing AI agents with a governed set of metrics and dimensions, moving beyond simplistic text descriptions or flat table interfaces that lack structural guardrails. E-Graphs allow for parallel application of rewrite rules, maintaining multiple expression forms and enabling optimal query plans by resolving cross-cutting interference issues. The future of Semantic SQL is anticipated to become a standard, accommodating more complex analytical workloads through SQL extensions, developed in collaboration with the Open Semantic Interchange working group.

Cube has evolved significantly since its inception, transitioning from a focus on a standalone semantic layer to becoming a comprehensive agentic analytics platform. Initially, Cube aimed to modernize the semantic layer by coding it, aligning with industry trends of treating analytics infrastructure like software. As the industry shifted towards fragmented BI stacks and AI-driven analytics, Cube recognized the importance of a flexible semantic layer that can integrate with diverse tools and support both human and AI collaboration. This led to the development of Cube Core, an open-source semantic layer, and Cube, a commercial cloud product that enhances Cube Core's capabilities, offering a full-featured platform for internal and embedded analytics. Cube Core remains focused on data modeling, access control, and pre-aggregations, with a new SQL API enhancing its expressiveness and flexibility. Cube, on the other hand, provides additional features, AI orchestration, and integration capabilities, making it suitable for organizations seeking a robust internal BI platform or embedded analytics solutions. As Cube continues to grow, it maintains strong integrations with other BI tools and spreadsheet applications, catering to diverse analytics needs while simplifying operational complexities for users.

Cube has introduced the Cube Slack Agent, an extension of its Analytics Chat, to facilitate seamless data analysis within Slack, acknowledging that many organizations conduct significant portions of their analysis and decision-making processes in this communication platform. The Slack Agent allows users to query the semantic layer directly from Slack, ensuring that responses align with established metrics and definitions, enhancing reliability over general-purpose language models. Each Slack thread corresponds to an Analytics Chat session, enabling users to interact with data through conversations while maintaining continuity in their analysis. The agent respects the user's permissions set in Cube, ensuring consistent access control, and necessitates a one-time setup by a workspace admin. Available on Premium and higher plans, the Cube Slack Agent aims to streamline analytics workflows, with upcoming features like in-channel mentions and enhanced sync capabilities, tailored to user feedback for future updates.