| Category | AI-native analytics engine with an integrated data stack | Transformation framework with an add-on metrics layer |
|---|
| Who it is built for | AI product and analytics teams, plus anyone who works with data — spreadsheet users through ML engineers | Analytics engineers who own the transformation layer |
|---|
| Primary interface | The agent you already use, over MCP — plus Workspaces, notebooks, reports and data apps for the people who want a UI. All of them consume the same model rather than being the place it lives | Code — models authored in SQL, Jinja and YAML through an IDE or CLI, with BI tools on top |
|---|
| Modeling language | Malloy — a modeling and query language with imports, inheritance, and public and private members | SQL with Jinja templating plus YAML, and MetricFlow for metrics |
|---|
| What is open | Open core. Malloy is open source, and we build and maintain Malloy Publisher, the open-source server for Malloy models. Your model is code in your repository, and Credible is in the Apache Ossie ecosystem for semantic interchange | Open core — dbt Core and MetricFlow are Apache 2.0, the platform is commercial, and MetricFlow is a reference implementation for Apache Ossie |
|---|
| How the model gets built | A coding agent with open-source MCP tools and agent skills, capturing context from where it already lives | Hand-authored models, with agent-assisted authoring |
|---|
| Governance | Governance as code. Access rules are annotations in the model itself — versioned, reviewed and composable like any other code | Lineage, tests and metric governance within the project |
|---|
| Materialization and caching | One annotation on the source, in the same file as the logic it materializes — no derived-table block, no rollup definitions, no refresh triggers, no orchestration run to schedule. Optional per source: query your own warehouse directly, or hold a source hot in Credible’s in-memory serving layer, which is how a team on Postgres gets fast serving without buying a warehouse to get it | Materializations are a core concept for transformation, but the Semantic Layer itself ships no pre-aggregation cache and compiles fresh SQL per query |
|---|
| How an agent finds the right data | Search. Typed targets — source, dimension, measure, view, even a dimensional value — are matched against an index of the model and come back ranked, so an agent asks for what it needs instead of picking a model and touring it | List then drill — list_metrics or get_all_models, then query_metrics or get_node_details |
|---|
| Where the model can be used | One model served to every surface — agents over MCP, plus APIs, an SDK, embedded dashboards, notebooks and HTML data apps. Results carry an interactive UI resource (MCP Apps, the official extension), so a client that supports it renders a real chart or table instead of the model re-narrating rows | Semantic Layer APIs into BI tools, plus an MCP server |
|---|
| Scale and portability | Built for globally distributed, high-availability workloads. Warehouse-agnostic on open-source Malloy — BigQuery, Snowflake, Postgres, MySQL, Trino, Presto and DuckDB, which also reads Parquet straight out of object storage including Azure Data Lake — so the model travels | Metric queries served through the hosted dbt Cloud Semantic Layer |
|---|
| What you pay for | Usage, not seats — unlimited users on every plan, so adding people never changes the bill. Metered per organization on tokens, bytes processed, bytes served and hot storage, starting free. Your own agent’s tokens are never billed, and a query that runs on your own warehouse is not metered for the scan — only for the result it hands back | Per-seat, plus event meters — models built, and metrics queried through the Semantic Layer |
|---|