Generating Slide Insights in Present Pro

A "Slide insight" is a natural language analysis of a slide that is dynamically generated at runtime using AI. Insights can be added to your slide as text fields or in a tooltip, and they provide your reader with a textual analysis of the content of the slide that changes dynamically as the data in the slide changes. For example, when you use the runtime Chatbot to add new measures to a visual at runtime any insight on that slide will regenerate to reflect your change.

Slide insights are generated in your Application Language and contain analytic information about the content (visuals and applied slicers) that is displayed at runtime.

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.

Slide Insights Content

When you open a slide or tooltip in your presentation at runtime, any Slide Insight variable is replaced with a block of generated text in your Application Language. The text is "analytic," describing the content of the slide that the variable appears on. The generated text reflects all visuals on the slide, even where the content is from different models, and also reflects the current interactive selections. For example, if you have made a selection from a drop-down, the Slide insights content will reflect that selection.

Slide insights typically generate a few paragraphs of text, although this may depend on your Settings.

What does the insight look like?

The analytic content looks different and is loaded at different times depending on your slide design.

What content does the insight contain?

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 content includes 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 selected to enable 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 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 about any bias that may disproportionally harm or benefit any particular group, particularly historically disadvantaged groups. The returned content is generated by the underlying LLM.

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.

Adding Insights to your slide

Add insights as a text field

If you add Slide insights as a text field the generated content is created at runtime when the slide is first opened. It is then refreshed whenever runtime changes are made. The advantage of using a text field is that your content is shown to the reader straight away.

Manual process: From the Toolbox

From the left-hand Toolbox:

  1. Right-click Add Text Field > Slide Insights.
  2. .

  3. Click the canvas at the point where you would like to add the text field.

  4. Clicking creates a standard sized item. Alternatively, you can drag your cursor to draw a box on the canvas indicating the size of the item when dropped.

  5. Select the text field on the canvas.
  6. The Slide Insights panel opens at the bottom of the page.

  7. Optionally, specify the settings for your Slide Insights.
  8. These options allow you to control the tone type and verbosity used by the LLM when generating the replacement text. For more information, see Settings.

  9. Click Apply.

Tip: You should probably resize your text field straight away. This is because the variable #SlideInsights will be replaced with at least a paragraph of text at runtime, so it's important to be sure that you leave enough space for the generated content.

Alternative process: Use the Chatbot

If you include a request to add Slide Insights explicitly to your prompt (you say or type "add insights" as part of your prompt), a Slide Insights text field (a text field containing the variable #SlideInsights) is added to your slide.

Add as a tooltip

If you add Slide insights as a tooltip the Slide insight content is not presented when you view the presentation at runtime, it is generated only when you hover over the asset at runtime. The content of the tooltip can be read out by Pyramid using its text to speech facility.

Tip: You should use a tooltip for your slide insight if you only want to load the insights when you want to view them. This can improve performance, as it means the generation does not have to happen at load time.

Manual process: From the Context Menu

  1. Drag the asset (a shape, image, or text field) onto your canvas.
  2. This is the asset that you want your user to hover over to open the tooltip. You can drag an asset from the Toolbox or add an Illustration from the Content panel.

  3. Right-click that asset and select Set Tooltip from the context menu.
  4. The Tooltip Designer dialog opens.

  5. From the Text Fields drop-down, select Slide Insights (orange arrow below).
  6. The #SlideInsights tag is added to the tooltip panel and the Slide Settings panel opens at the bottom of the dialog:

  7. From the Bubble Size option (green arrow above), select Auto.
  8. This setting ensures the Smart insights content fits into the tooltip bubble in the runtime presentation.

  9. Optionally, specify the settings for your Slide Insights in the Settings panel.
  10. These options allow you to control the tone type and verbosity used by the LLM when generating the replacement text. For more information, see Settings.

  11. Click Apply to save your settings.
  12. Click OK to save the details of your tooltip and close the dialog.

Alternative process: Using the Chatbot

If you are using the Chatbot to create your slides and you do not indicate that you want to add Slide Insights explicitly in your prompt, a Gen-BI icon is added to your slide automatically. At runtime, your reader can hover over this icon with their cursor to view the AI generated insight information as a pop-up. Note: This functionality speeds up the load time for the presentation, since the Smart Insights are only populated when the user hovers over the icon.

  • Click here to learn to build a presentation using the Chatbot

Editing and Deleting #SlideInsights

You can edit and delete #SlideInsights like any other text field. Be aware that the tag will be replaced with a lot of text when it is rendered at runtime, and plan its appearance and position accordingly.

  • Click here for more information about Variable Text Fields

Settings

Open the Settings dialog by clicking the variable on the canvas:

These settings are used by the LLM when generating the Insights:

  • User Tone Type: Sets the appropriate tone for the insight message. This can be one of a set of tone values ranging from Professional to Whimsical.
  • LLM Verbosity: Sets the level of detail to use for the explanation in the generated insights. This can be one of Low, Medium, or High.

Tip: If you *always* want to select a particular Tone type or Verbosity, you should reset your user defaults to save time in future. For more information, see User Defaults.