When you open a page in your output publication or a slide in your runtime presentation, any Insight variable (#PageInsight or #SlideInsight) is replaced with a block of generated text that was returned by your LLM in your Application Language. Insight text is "analytic," describing the current content of the page including any applied filters and optionally also incorporating a "fairness analysis." The insights content is typically a paragraph or two, although this may depend on your Settings.
Note: You can only make use of this functionality if your administrator has selected the Enable Generative AI checkbox in the AI Settings page of the Admin Console. If your administrator does not select this option, the function is not available for use.
Warning: When using LLMs, your assets are generated using public domain algorithms. This can produce erroneous and inconsistent or random results. Use at your own risk.
Insights Content
Insights can be added to your publications or presentations as follows:
- You can add a
#PageInsightsvariable to your publication in Publish Lite or Publish Pro. The replacement text is generated by the LLM at build time and describes visuals on the page and reflects any filtering. - You can add a
#SlideInsightsvariable to your presentation in Present Lite or Present Pro. The replacement text is generated by the LLM at runtime and is updated interactively in response to runtime changes, such as slicer selections.
Tip: In Present Pro, you can add your variable either as a text field that gets replaced on launch or in a dynamic tooltip. Where a tooltip is used, the tag is not replaced on load but only when the tooltip is opened (when your reader hovers their cursor over the tooltip icon).
Analytic Content
Basic Insights
The insights are generated in the current user's chosen Application Language, including being presented as right-to-left text where that language is Hebrew or Arabic. The analysis contains information from the following categories:
- Basic Facts: Standard metric analysis, including the average, maximum, minimum, dispersion, median, and standard deviation.
- Pareto Analysis: The value's total, top n, and bottom n that account for a certain percentage.
- Relationships: Any positive or negative metric correlations, relationships, and a correlation statistic.
- Trends: Uses regression analysis with r-squared and slope coefficients to explain how changes to a metric affects another metric, the closeness of fit score, and the slope correlation
- Forecasts: Best fit forecasting (across eight different algorithms) if the query contains a date-time hierarchy to predict whether a value will increase or decrease over a certain period and by how much, with the range of fluctuation
- Outliers: Displays the top three most outstanding data points in the query. It also shows the probability density for each outlier.
- Categorical Analysis: Depending on the amount of data in the query, categorical insights may display information about comparatives, correlations, and forecasts.
Fairness analysis
If you are using an LLM to generate Pyramid content, and your administrator has enabled Fairness Analysis in your AI settings, then some fairness analysis content will be generated by the LLM and added to the content in your Smart Insights panel or any Slide or Page Insights added to your presentation or publication, respectively.
The fairness content, generated by the underlying LLM, is created through an analysis of the measures and attributes used in the discovery (but not the values of those measures and attributes) and provides insights into any bias that may disproportionally harm or benefit any group, particularly historically disadvantaged groups.
Important: The fairness content will be regenerated by the underlying LLM whenever the Smart Insights panel is opened, at runtime whenever the presentation is refreshed, or whenever a new publication is built. Each time it is regenerated, the content may change.
Related information
Smart Insights
In addition to Slide insights, you can also view Smart Insights in your presentation at runtime. These insights are accessed from the Smart insights panel tool or on-the-fly using the Chatbot. When using the panel tool you can filter your insights to contain light, advanced, or categorical levels of detail.
They provide analytic information about the specific discovery they are associated with, and let
- Click here for more information