Most GenAI projects stall at the same spot: the model doesn't know what your data actually means. A semantic layer fixes that - a definition layer that sits on the database you already have and makes it legible to LLMs and agents. No migration. No new data team to hire.
And it's not just tables anymore. Semantido now covers Kafka streaming schemas, enforces grain and definition quality with built-in lint checks, and separates meaning from deployment so your definitions travel with your data — from warehouse to topic to agent. On one production pipeline, this took text-to-SQL accuracy from ~50% to ~90%, benchmarked against a pure schema-in-context baseline.
I'm a physicist by training, an engineer by trade, and spent the last 14 years building systems and data architectures in banking and capital markets, the kind of environments where "the number is wrong" isn't an option. Creator of the open-source semantic layer semantido.
Explore my long-form articles on leveraging semantic layers, or Book a free consultation
Companies I previously worked with
v0.5 is the release where semantido stops being a descriptor and starts enforcing it. the three features of this release are grain - at which a concept identifies itself, a separate groundings document splitting meaning from deployment bindings and a linter that runs a sqlglot with ten static checks.
semantido v0.4.1 ships a concept registry: three families of typed edges that let two agents who have never shared a schema disagree safely about what a word means, no OWL, no reasoner, ~100 lines of protocol.
semantido 0.3 ships a first-class time-dimension model, alongside a complete exporter overhaul that serializes one semantic layer as OSI YAML, Markdown, and JSON. This article explains why the two belong in one release: curated metadata is the difference between an AI agent finding eight false time axes or finding the right one.
This article provides Chief Data and Analytics officers with a strategic guide for navigating the crowded semantic layer landscape, demonstrating why a robust definition system is a critical infrastructure dependency for both GenAI and agentic systems across six distinct vendor categories.