| Category | AI-native analytics engine with an integrated data stack | Agentic analytics on a context graph the platform discovers and keeps learning |
|---|
| Who it is built for | AI product and analytics teams, plus anyone who works with data — spreadsheet users through ML engineers | Business teams — finance, marketing, sales, operations — asking without a BI project first |
|---|
| 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 | Chat — in Genloop, in Slack, and from MCP clients including Claude Code and ChatGPT |
|---|
| Modeling language | Malloy — a modeling and query language with imports, inheritance, and public and private members | None to author. The context graph is discovered from schema and documents, then refined by use |
|---|
| 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 | Vendor-owned, and model-agnostic — it can run air-gapped, with no external LLM calls |
|---|
| How the model gets built | A coding agent with open-source MCP tools and agent skills, capturing context from where it already lives | Auto-discovered, then corrected in a Review Center where the data team approves what it learned |
|---|
| Governance | Governance as code. Access rules are annotations in the model itself — versioned, reviewed and composable like any other code | Role-based access enforced per conversation, with a review loop over what it learns; SOC 2 Type II and ISO 27001 |
|---|
| 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 | Reads in place and stores no copy, so performance stays with the source system |
|---|
| 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 | The context graph, plus routing along investigation paths that have been run and verified before |
|---|
| 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 | Chat, Slack, embedded analytics and MCP, with one shared context so a correction made in one place holds in the others |
|---|
| 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 | Reads existing sources without migration; deployable in cloud, VPC, on-premises or air-gapped |
|---|
| 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 | Credit tiers — a free monthly grant, then paid plans that each include a pool of credits |
|---|