ThoughtSpot introduces Spotter Semantics semantic layer

ThoughtSpot introduced Spotter Semantics, a semantic layer intended to convert raw, fragmented data into governed, machine-readable business context that Artificial Intelligence (AI) agents can interpret and act on at enterprise scale.

The company said the capability sought to provide consistent answers across different users and agents by supporting natural language queries and by using a patented search-token architecture alongside ThoughtSpot Modeling Language (TML) to represent business context.

Technically, Spotter Semantics included a context-aware translation engine that converted natural language into Structured Query Language (SQL) via a specialized query generation engine and AI-powered indexing, a knowledge-graph based semantic architecture that encoded business logic, security rules, metric definitions and model instructions, aggregate-aware query routing between detail and pre-aggregated tables, a governed Metrics Catalog, Continuous Integration (CI) and TML for automated deployments with rollback, and interoperability through a Model Context Protocol (MCP) server and Open Semantic Interchange standard with Snowflake, Databricks and dbt.

The release also provided tools for analysts to create custom metrics, cohorts and calendars through a visual UI, for data engineers to prepare underlying data with SQL, and for developers to manage deployment via APIs; ThoughtSpot reported the platform grew 133% year on year by the end of fiscal 2025 and said over 64% of customers used Spotter as their primary AI analyst.

“The core challenge for modern BI agents is the lack of full context needed for precise, accurate and trusted answers,” said Francois Lopitaux, SVP of Product Management at ThoughtSpot. “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.” “That helps us enrich our semantic layers based on how they look at data,” said Manbir Paul.

ThoughtSpot said future capabilities were set to include writeback for actionable analytics and Federated AI Search.