Best Practices

To get the most relevant and accurate answers from Holistics AI, follow these best practices.

What's good for users is good for AI

If you weren’t building for AI, how would you document your data products to give users the best experience - how easy is it to find the right dataset or dashboard, and how reliable are your metric calculations? Apply the same user-first standards and AI will benefit too.

Write clear, descriptive names

Use clear, descriptive names for datasets, models, metrics, dimensions, dashboards, and widgets. This helps both users and AI find the right objects quickly.

Use tags to flag trusted data

AI uses tags to prioritize trusted and relevant items in its answers. For examples, it will prefer a trusted dataset and avoid an archived one.

Refer to Tags on how to set these up.

Encapsulate logic in formulas

To keep answers accurate and consistent, encode business logic in metric and dimension formulas - especially for ambiguous terms or complex rules.

Example - “Active User” with description and formula:

metric active_user_count {
	label: 'Active user count'
	description: '''
        Active users are those who placed at least one order in the previous month
    '''
	definition: @aql
	  ecommerce_orders 
	  | where(ecommerce_orders.created_at is @(last month)) 
	  | count_distinct(ecommerce_orders.user_id)
}

Provide additional context

Document synonyms, operational rules, and caveats in the object description so AI can interpret intent correctly.

Example - operational context on a metric:

metric return_ratio {
   label: "Return Ratio"
   description: '''
      Product quality issue: If the return ratio of a particular product_id is 
      higher than 30%, it means the product has quality issues 
   '''
   definition: @aql safe_divide(return_amount, gross_sales)
}

Leverage configurations from other features

When you customize underlying tables and common breakdowns to improve users’ exploration, Holistics AI also uses these configurations as context for its analysis and follow-up suggestions.

For example, if Revenue has predefined underlying tables - Orders, Users, and Products - AI can propose targeted investigations during a Revenue drop, such as surfacing top canceled orders, identifying churned users, or listing lowest‑selling products.

Use AI to enhance AI

Holistics AI includes built-in features that help you enrich data context quickly and at scale.

Create field descriptions with AI

Holistics AI helps automatically generate clear, contextual descriptions for your data fields. This helps business users to understand data fields better, as well as improve the quality of AI queries by providing better context.

Create tag descriptions with AI

Holistics AI quickly generates meaningful descriptions for your tags based on the tag name, user-provided keywords, or conventions from existing tags in your workspace. This improves documentation consistency and enhances context for other AI features.

Create metrics and dimensions with AI

The most reliable way to encode business rules is to turn them into reusable metrics and dimensions. Use Ask AI to draft fields quickly, then review the logic, and promote them back to the dataset for future analysis.