ThoughtSpot

Agentic Semantic Layer for AI Agents

An agentic semantic layer is a metadata layer between AI agents and a data warehouse that defines governed metric definitions, enforces access control, and exposes programmatic query interfaces (e.g., MCP or REST/SDKs). Unlike legacy semantic layers built for BI dashboards, an agentic semantic layer is designed for programmatic consumers (LLMs, AI agents, SDKs) and requires machine-readable metric definitions, programmatic discovery/querying, structural multi-tenancy, pre-aggregation to handle high query volume, and schema-as-code with version control. It generates SQL from governed definitions (not from LLMs), scopes queries per-tenant via publishable keys, and returns auditable, consistent results. The article compares existing tools (Cube, dbt MetricFlow, Looker, AtScale, ThoughtSpot, Bonnard) and explains how the agentic layer fits into the modern data stack on top of ingestion, warehouses, and dbt transformations.

ThoughtSpot Named a 2026 Gartner® Magic Quadrant™ Leader for Analytics and BI Platforms

ThoughtSpot has been recognized as a Leader in the 2026 Gartner Magic Quadrant for Analytics and BI Platforms, with a dedicated report available for download.

Postgres pattern to query row state as of a time

The article presents a Postgres schema pattern for answering point-in-time questions like “what did this row look like at T?” by keeping a history table alongside the main table (SCD Type 4) and using a row-level trigger to mirror INSERT/UPDATE/DELETE operations into that history table. The author contrasts common alternatives — event sourcing, in-place versioning (SCD Type 2), and periodic snapshotting — and provides concrete SQL: history table creation (LIKE ... INCLUDING DEFAULTS), a trigger function that stamps valid_from/valid_to and writes tombstone rows on DELETE, a point-in-time SELECT that picks the version valid at :as_of, and a backfill pattern for pre-install rows. The piece also warns about operational concerns such as schema drift when adding columns and recommends automating schema migration for history tables.