Meta:Context: a business context schema in dbt's semantic layer

AI needs business context to deliver useful insights about enterprise data: what numbers mean, how to investigate anomalies, what to do about them. 

Drawing on expert works in semantics and ontology, we built a 5-layer, 36-field schema that encodes business and metrics knowledge in dbt's existing meta: block. It flows through the Semantic Layer API with no new tooling required.

In simulations, Claude Haiku with structured meta context matched Claude Opus with scattered documentation; the schema preserves meaning well enough that a small, fast model reconstructs high-quality analytical reasoning from it.

This session covers the schema design, expert foundations, the simulation evidence, and where to start: one metric, three fields, one question.