Displayr AI incorporates advances in AI technology into our software to make it easier for you to analyze your data. These methods are built on the latest AI technologies to provide new and improved features in the software. You can opt out of Displayr AI on an account-level basis. Our current home-grown AI offerings remain available for those who decide not to opt into tools that utilize that specific technology.
This article covers:
Opting In or Out of AI Functionality
Displayr AI
By default, any Displayr account created after October 1, 2025, is automatically opted into Displayr AI. To disable Displayr AI, go to your Account settings via the initials icon in the upper right corner of your Displayr screen, and then navigate to General > Displayr AI and Disable Displayr AI. To enable Displayr AI features on your entire account, you must Enable the feature via the dropdown in Account Settings > General > Displayr AI and accept the Displayr AI - Terms of Use. More detailed information about this is found in Opting In or Out of Displayr AI.
Displayr AI Assistant
A user can turn this off in the user interface by clicking the user's initials in the top-right of Displayr and choosing Disable AI Assistant.
Features
Chat
You can chat with Displayr to help you quickly clean and tidy your data, and build, analyze, visualize, and share your report in minutes. In addition to built-in prompts, you can ask the Chat about how to perform any task in Displayr, and it will guide you through the steps and provide links to related Help documentation (if you have not opted out of Displayr AI Assistant). See Chat for more details.
Research Agent
When Displayr AI is enabled, Research Agent can be used to automatically analyze data and write a report. You provide data and guidance on what questions and information you want covered in the report, and Research Agent automatically analyzes the data and creates the report for your review. See Research Agent for more details.
Data Preparation Agent
Use the Data Preparation Agent to clean and tidy your data set. This can be run independently from the Data Sources tree, or as part of the Research Agent process. This allows you to spend less time doing data preparation tasks and automatically clean and tidy your data. It improves the quality of analyses and gives you more time to actually dig into findings. See How to Automatically Check and Prepare Your Data with Data Preparation Agent for details.
Better Auto Text Classification
When Displayr AI is enabled, automatic classification done within the Text Categorization tool will use the new, better classification feature. The new feature is better at arriving at sensible categories as well as classifying responses into the appropriate themes. The automatic classification is done by clicking the Create and Classify buttons in the Text Categorization tool itself. You will be notified that Displayr AI is being used in the progress window that pops up:
If Displayr AI is not enabled, the categorization tool uses Displayr's proprietary modeling algorithm to create themes as before. However, for both methods (Displayr AI or modeling algorithm), you will have the ability to specify the number of themes that are created - the default is 10:
You can see the difference in the classification models in the results below, based on the question "What are the main differences in cola drinkers?" The modeling algorithm classification is on the left, and you can see some themes are not useful/nonsensical, whereas the Displayr AI themes on the right are much more relevant.
You can use custom AI prompts to refine your themes and classification during text categorization for an additional AI boost. Read more at Optimizing Text Categorization With Custom Prompts.
Better Variable Set Labeling on Combine
When Displayr AI is enabled, when you Combine variables together into a variable set, the AI will automatically determine the variable set name. You can always Rename this afterward if need be. These labels will be retained if you later update the data (see note below for more details). Previously, variable sets were labeled based on matching text across variables; see How Variable Sets/Questions are Automatically Grouped and Labeled for more detail. You can see an example below. The variable set name q2 on the left was originally used due to the label pattern matching, whereas the Displayr AI variable set name on the right is much more descriptive:
Customizable AI Outputs and Variables
In addition to the features above, Displayr has AI tools that allow you to create your own outputs and variables. Each feature is created with a default prompt and optional input fields. These are fully customizable in the object inspector or the code editor panel. See Using Customizable Displayr AI Features for details.
AI R Code Writer
Need some help writing R Code for custom calculations and variables? AI can help you write R code directly in the code editor. See AI R Code Writer for more information.
Technical details
Note on updating data
When Displayr AI is used for labeling variable sets as a step in the Data Preparation Agent and on Combine, it is akin to manually changing the default labeling. That is, these labels will be retained when the data set updates. If you want to ensure that your labeling is updated based on new data files, you should not use Displayr AI for tidying labels and disable it in your Account Settings so it does not relabel things when you Combine.
Nature of AI results
AI tools are, in general, not deterministic. As in, they don't give the same answer every time you run them. It's the nature of the tool itself, and if you have played around with ChatGPT, Gemini, GPT-4o, etc., you have probably experienced this yourself. Thus, while results are still smarter than what you can typically create via traditional machine learning alone, they are not perfect and sometimes can give subpar or nonsensical results. The implications of this are:
- If you receive poor results, try running the feature again to see if it improves.
- If there is an error or the feature does not work as expected, please take a screenshot of the issue and forward this along with a link to the document to support@displayr.com. Saving the result and noting the date/time will allow teams to more closely review the data to see what might have happened. So, for example, if you get a bad outcome in a text categorization, be sure to save the categories to the data set.
Feedback like this is valuable as it can help identify potential issues that need to be addressed by our developers.
Availability
Displayr AI is available on a regional basis to comply with region-specific data governance in USA, Australia, Europe, and Canada. In South East Asia, data sent to Displayr AI for processing may leave the geographical region due to a lack of necessary infrastructure. Users with the free version of Displayr do not have access to these features.
You can read about it in more detail at Displayr AI - Terms of Use.
Next
Using Customizable Displayr AI Features
How to Automatically Check and Prepare Your Data with Data Preparation Agent
Getting Started with AI Prompting in Displayr
Optimizing Text Categorization With Custom Prompts