| Category | AI-native analytics engine with an integrated data stack | Microsoft BI, now part of Fabric, with semantic models in DAX |
|---|
| Who it is built for | AI product and analytics teams, plus anyone who works with data — spreadsheet users through ML engineers | Microsoft-standardized enterprises, from analysts to finance teams |
|---|
| 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 | Its own UI — Power BI Desktop to author, the service to consume, with Copilot alongside |
|---|
| Modeling language | Malloy — a modeling and query language with imports, inheritance, and public and private members | DAX and M — highly expressive, with an implicit evaluation-context model that takes years to master |
|---|
| 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 — DAX, M and the semantic model are Microsoft formats |
|---|
| 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 in Power BI Desktop; Copilot answer quality depends on descriptions and synonyms you write |
|---|
| Governance | Governance as code. Access rules are annotations in the model itself — versioned, reviewed and composable like any other code | Row-level security in the model, plus Fabric and Entra ID permissions |
|---|
| 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 | In-memory VertiPaq import, DirectQuery, dual storage and aggregation tables; Direct Lake reads Parquet from OneLake without importing. Mature, and the main performance lever |
|---|
| 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 and inspect — browse workspaces, list datasets, fetch the model definition, then run DAX |
|---|
| 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 | The Power BI service, embeds, Fabric and the XMLA endpoint; strongest inside Microsoft |
|---|
| 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 | Scales with Fabric capacity, and the semantic model is a Microsoft format |
|---|
| 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-user licences plus reserved Fabric capacity, with Copilot drawing on that same shared capacity |
|---|