How AI interprets your data
Basedash performs automatic pre-processing when you connect your data sources to understand the structure of your schemas, tables, and columns. The AI can analyze data types, relationships, and basic metadata to generate queries and visualizations. However, custom context provides the business intelligence that goes beyond the technical structure. It helps the AI understand:- How your organization operates and what metrics matter most
- What your data actually represents in business terms
- Internal terminology and KPIs specific to your company
- The context and meaning behind complex data structures
How it works
Custom context is automatically considered by the AI whenever you create charts, chat, or reports in Basedash. Organization-wide context applies to every conversation within your organization, while schema and column-level context is used when that specific data is referenced by the AI.Accessing custom context
Organization-wide context
You can access organization-wide custom context through the command bar:- Press Command + K to open the command bar
- Type “custom context” and select the option
- Enter your organization-specific information

Context in chat
You can also add context directly in the chat interface:- Look for the “add context” button (plus icon) in the bottom-left of the chat input
- Click to add relevant context for your current conversation

Data source context
To add context for specific data sources, schemas, tables, or columns:- Navigate to Data sources by:
- Clicking the workspace dropdown in the top-left corner and selecting “Data sources”
- Or pressing Command + K and typing “data sources”
- Select any data source or schema
- Look for the “add description” option

Best practices
Start with organization context
We recommend beginning with organization-wide custom context as one of your first setup steps. This provides the AI with fundamental understanding of your business, terminology, and key metrics.When to add schema and column context
Only add schema and column-level context when the names or existing descriptions aren’t sufficient for the AI to understand the data. This is particularly helpful for:- Complex JSON columns: Add context to explain what data is stored within JSON structures
- Unclear schema names: Provide context about what type of data is stored and how it’s used
- Custom data structures: Explain any non-standard data formats or relationships
Define internal terminology
Use custom context to define:- Internal KPIs: Specific metrics that only your organization understands
- User terminology: How you refer to different user types (e.g., “signups,” “active users,” “premium customers”)
- Business jargon: Company-specific terms and definitions
- Metric definitions: Custom calculations or business logic for specific metrics