Diagram (Schema)
The Diagram (Schema) tool provides a visual representation of data models and table relationships. It helps developers and AI agents understand how datasets are structured and connected, making data exploration, analysis, and reasoning more accurate. This tool can also be enabled for AI agents, allowing them to interpret relationships between tables when answering questions or generating insights.
The Diagram tool is designed to:
Visualize relationships between tables
Clarify one-to-one, one-to-many, and many-to-many relations
Serve as a reference for data modeling and analytics
Provide structural context to AI agents
How to configure diagrams
Access the diagram via the icon in the side menu
Inside Settings, it is possible to define a clear name for the schema or diagram.
Describe the purpose and scope of this schema.
Define the column used to filter user-related data.
In the tables tab, users can select and filter the tables they want to drag onto the canvas.
After dragging the desired tables, the user can create relationships between the databases using the keys for each table.
After relating the tables, it is possible to define the relationship cardinality.
Click the Save button to persist the schema configuration.
Access the diagram configured in the Diagrams tab at the panel.
These relationships help both users and agents understand:
How data flows
Which tables should be joined
Where aggregations make sense
How AI Agents Use the Diagram
When enabled for an AI agent, the Diagram allows the agent to:
Understand table relationships before querying
Choose correct join paths
Avoid incorrect assumptions about data structure
Explain results with structural context
Best pratices
Keep schemas focused and domain-specific
Use clear and consistent naming
Define user filter columns when applicable
Avoid overly complex diagrams in a single schema
Enable diagrams only for agents that need structural understanding
A clean schema improves both human and AI comprehension.
Last updated