| Category | The AI Analytics Engine — you write down what data means, and it generates the stack under it | Four products, one per layer — Fivetran to land the data, Snowflake to hold it, dbt to shape it, Looker to show it |
|---|
| Who it is built for | The whole organization, not one central team — ops, finance and product; spreadsheet users through AI engineers | A central data team with the budget for four vendors and the people to run them |
|---|
| Primary interface | The agent you already use, over MCP — plus Credible Workspaces, data apps, dashboards, notebooks and reports for the people who want a UI. Every one of them reads the same model, and the model lives in your repository | Looker dashboards and explores for everyone else; dbt and Fivetran consoles and code for the data team |
|---|
| Modeling language | Malloy — a modern programming language for data: imports, inheritance, public and private members, and queries that compose into new sources | SQL and Jinja in dbt, then LookML in Looker — two models of the same data, kept in step by hand |
|---|
| What is open | Open core. Malloy is open source, and we build and maintain Malloy Publisher — the open-source server for Malloy models, and where our agent skills and MCP retrieval tools are open source too, runnable in any agent with no Credible account. Your model is code in your repository, and Credible is in the Apache Ossie ecosystem for semantic interchange | dbt Core is Apache 2.0; Fivetran, Snowflake and Looker are commercial, and LookML is Looker’s own format |
|---|
| How the model gets built | Model first: you write down what data means, and the engine derives the pipelines, storage and serving from it. Open-source MCP tools and agent skills help you capture that meaning from where it already lives, running in your coding agent | Hand-authored by analytics engineers: dbt models first, LookML on top, each with its own review and release cycle |
|---|
| Governance | One annotation on the source, in the same file as the logic it governs — no grant objects to declare, no rule to re-attach on every surface that exposes the data, no attribute table kept in step by hand. A row filter or an authorize gate over attributes the server resolves from verified identity, and everything reading that source inherits it: dashboards, notebooks and agents alike | Split across the layers — warehouse roles, dbt tests, Looker access filters — and reconciled by the team that runs them |
|---|
| 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 own storage, which is how you get fast serving without buying or banging your head against a warehouse to get it | dbt builds tables on a schedule; Looker adds persistent derived tables and caching; each is configured and kept warm by hand |
|---|
| 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 | Looker’s MCP server walks the API — models, then explores, then fields — before an agent can query |
|---|
| 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 | Looker’s UI, embeds and API plus its MCP server; dbt’s Semantic Layer APIs for other tools |
|---|
| Scale and portability | Globally distributed, high-availability serving that scales horizontally — workers scale out under load rather than being sized in advance. Warehouse-agnostic on open-source Malloy, and the model is portable because the language is | Each layer scales on its own terms and its own bill; the warehouse is the one place the data lives, so everything routes through it |
|---|
| What you pay for | Usage, not seats — unlimited users on every plan, so adding people never changes the bill. Three meters, pooled per organization and starting free: tokens, compute time and storage. Your agent’s own LLM tokens are never billed to you, and a query that runs on your own warehouse is not metered for the compute — only for the result it hands back | Fivetran by rows synced, Snowflake by compute credits and storage, dbt Cloud and Looker per seat — four bills, summed, before the people |
|---|