ThoughtSpot introduces Spotter Semantics, a semantic layer designed to deliver consistent, reliable insights to AI agents and business users. The platform converts raw data into managed business context via a search token architecture.
Francois Lopitaux, SVP of Product Management at ThoughtSpot, explains the core of the approach. “From day one we’ve placed an emphasis on an AI-native semantic layer that serves as the bridge between complex data and business-ready answers. Critically, this deterministic approach relies on our patented search tokens, not text-to-SQL powered by LLMs, which is why we can guarantee the most consistent, trustworthy insights on the market.”
Spotter Semantics combines a specialized query generation engine with AI-driven indexing. The system uses knowledge graphs that integrate business logic, security rules, metric definitions, and model instructions into a machine-readable format. Another new feature is Aggregate Awareness, which automatically forwards queries to the detail level or pre-aggregated tables, depending on the specific question. This should reduce response times and lower computing costs.
A Metrics Catalog also serves as the central source of “single version of truth.” Analysts can create metrics, cohorts, and calendars themselves via a visual interface, while data engineers prepare the underlying data via SQL.
Open standard and MCP integration
ThoughtSpot is a founding member of the Open Semantic Interchange (OSI) standard, providing a vendor-neutral abstraction layer between cloud data warehouses and the AI experience layer. Through the ThoughtSpot MCP (Model Context Protocol) server, organizations can directly connect their semantic layer to any AI agent or LLM, including Snowflake, Databricks, and dbt.
Future enhancements to Spotter Semantics include writeback for actionable analytics and Federated AI Search.
Tip: ThoughtSpot aims to make data AI-ready with Analyst Studio update