| Category | AI-native analytics engine with an integrated data stack | AI data analyst over the whole stack, with an ontology layer and a warehouse of its own |
|---|
| Who it is built for | AI product and analytics teams, plus anyone who works with data — spreadsheet users through ML engineers | Enterprise data teams, and the business users whose questions queue behind them |
|---|
| 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 — threads with Ana in the TextQL app, in Slack, and from any MCP client |
|---|
| Modeling language | Malloy — a modeling and query language with imports, inheritance, and public and private members | .tql — a SQL-native semantic layer format, kept as reviewable files in a git-backed ontology repository |
|---|
| 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 format, with the ontology itself kept as files in a repository you control |
|---|
| How the model gets built | A coding agent with open-source MCP tools and agent skills, capturing context from where it already lives | Ana maps relationships across the connected sources, and .tql files are authored and reviewed on top |
|---|
| Governance | Governance as code. Access rules are annotations in the model itself — versioned, reviewed and composable like any other code | Role-based access control with SSO and SCIM, and role and tenant rules declared in the ontology |
|---|
| 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 | A purpose-built warehouse running inside your environment, so exploratory work over raw data does not wait on modeling |
|---|
| 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 | Ana works from the ontology and its connectors, and picks its own tools per question rather than walking a fixed sequence |
|---|
| 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 | Threads in the app, Slack, playbooks scheduled to email, embeds, a v2 REST API, and Ana itself as 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 | Over 50 connectors — warehouses, BI tools and SaaS APIs — deployed as SaaS, in your VPC, or on-premises by Helm chart |
|---|
| 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 | A tiered subscription carrying a monthly allowance of Agent Compute Units, with overage beyond it and no per-seat charge |
|---|