dbt Semantic Layer
Connect every dbt Semantic Layer metric and dimension to the warehouse tables, source systems, BI tools, and AI agents that depend on them.
Semantic Layers & BIWhy dbt Semantic Layer matters
The dbt Semantic Layer is the contract between the business and every agent querying the data. AI agents rely on MetricFlow definitions to pick the right metric, grain, and joins. But business definitions change constantly and the semantic layer has no visibility into whether its definitions still reflect upstream reality, whether they are consistent with definitions in other tools, or which agents depend on them.
Typedef connects every MetricFlow definition to the full lineage chain and every downstream consumer, so teams can catch semantic drift, reconcile metrics across tools, and scope definition changes before they reach agents.
What Typedef unlocks
Semantic drift detection
Surface when upstream changes have made semantic definitions stale so teams can update them before agents start producing wrong answers.
Cross-tool metric reconciliation
See where dbt Semantic Layer definitions align with or contradict metrics in BI tools and other semantic layers across the platform.
Agent consumption tracing
Follow a metric from its definition through the warehouse into every BI tool, application, and AI agent that consumes it.
Impact analysis before definition changes
Before modifying a metric or dimension, see every downstream consumer affected: dashboards, reports, reverse ETL syncs, and agent queries.
Related integrations
Verify that every metric means what you think it means, from definition to source.
Surface the business logic hidden inside LookML so impact analysis doesn't stop at the BI layer.
See which Hex notebooks and published apps break when upstream data changes, even the ones nobody formally tracks as production.
Trace any Cortex answer back through the semantic layer, warehouse, and source systems so users can verify why the agent produced a specific result.