Holistics AI
🚀 Holistics AI is now in alpha! Read our announcement and join our waitlist to be among the first to try it.
Introduction
Holistics AI is your thought partner for self-service analytics. Instead of writing code, dragging and dropping fields, or waiting for an analyst, you can simply chat with your data using natural language to explore insights and build visualizations.
Built on top of our governed semantic layer and composable query language, Holistics AI is designed to help teams explore data through conversation while staying grounded in trusted, curated datasets.
Getting access
Holistics AI is currently in alpha. If you're interested in trying it out:
- Join the waitlist
- We'll contact you when access becomes available
- Your organization admin can enable/disable Holistics AI in workspace settings
AI data policy
Data provided to Holistics AI
Holistics AI ensures a secure and transparent approach to data processing. To provide helpful, context-aware responses, Holistics AI may access different kinds of data. These data types include:
-
Metadata: Information of Holistics objects that the user is currently working with. This includes titles, labels, descriptions, text blocks, data types, model relationships, formulas, chart settings, AMQL codes, and git commit messages.
-
Sample Data: A few sampled values of the source database columns that the user is currently working with.
-
Result Data: Result data (in the form of csv and images) of the charts that the user is currently working with.
We currently use the OpenAI API. All processing follows OpenAI's usage policies.
Data shared by features
Each AI capability uses only the data it needs. You stay in control of what’s shared.
| Mode | Metadata | Sample Data | Result Data |
|---|---|---|---|
| Explore Data (with thinking) | ✅ Yes | ❌ No | 🟡 Optional Allow the AI to provide summary, insights, and analysis on the result. |
| Search Docs | ❌ No | ❌ No | ❌ No |
You can manage data sharing under Settings -> AI Settings -> Data Provided To AI.