← Back to overview The platform

A semantic layer for the AI-native stack.

One thesis, carried by every module: compile a structured query to SQL, push execution down, and serve the hot path from pre-aggregated data.

How the platform pieces fit together Any warehouse dialect feeds a governed Semantic Model, which the Join Graph and compiler resolve into correct SQL, cached as Rollups. REST and MCP consumers read from that pipeline. Tenant isolation wraps every box in the pipeline — each tenant's warehouse, model, and rollups stay physically separate. TENANT ISOLATION — every box, every request Any warehouse Snowflake · BigQuery · Postgres · MySQL · DuckDB Semantic Model entities · dims · metrics Join Graph compiler resolves the join Rollups pre-aggregated cache REST MCP
Everything left of REST/MCP is tenant-isolated end to end — a different tenant's query never crosses into your warehouse, model, or rollups.

A governed business model

Entities, Dimensions, Measures, and Metrics map your physical tables to business vocabulary — independent of any storage dialect.

Semantic Model

You never write the join

Name the metrics and dimensions you want. The compiler traverses the Join Graph and generates fan-out-safe SQL — correct even across one-to-many.

Join Graph

Sub-second hot path

Embedded and BI queries are served from pre-aggregated rollups by DuckDB over Parquet. Benchmarked p99 ≤ 14ms.

Rollups · p99 ≤ 14ms

LLM-native by design

Agents call MCP tools that emit a structured Semantic Query — never raw SQL. No hallucinated joins, no wrong numbers.

MCP

Multi-tenant, bring your own

Every tenant brings its own warehouse connection. Secrets are AES-256-GCM sealed; rollups are physically tenant-partitioned; RLS rides every read.

Isolation by design

Any warehouse, one port

Snowflake, BigQuery, Postgres, MySQL, DuckDB — each a renderer behind a single closed Dialect port. We generate SQL, never parse it.

Multi-dialect
See it end to end

See what a query looks like against this model.

The platform is the pieces — the query interface is what using them actually feels like.

See a live query Console