Skip to main content

Data Modeling Overview

Data modeling in Wren AI turns raw source tables into business-friendly structures that both people and the AI service can understand.

Use the Modeling section to:

  • define models for the tables in your data source
  • add descriptions and semantic metadata
  • create calculated fields and reusable logic
  • define relationships between datasets
  • save query results as views

What you can do in the Modeling page​

Models​

Models are the core building blocks in Wren AI. A model combines table structure, metadata, relationships, calculated fields, and other semantic details so the data is easier to explore and query.

Views​

Views are virtual tables built from existing models. They let you save and reuse query logic without storing a separate copy of the data.

In Wren AI, you can create a view from thread results by using Save as view.

Relationships and ERD​

The Modeling page includes an entity relationship diagram (ERD) that shows your models, views, and the relationships between them.

  • Models appear in blue.
  • Views appear in green.

erd