AIP features in Quiver

Quiver's AIP features are designed to help you perform data analysis using natural language prompts. In addition to getting helpful responses from AIP Assist on questions related to Quiver, users can use:

• AIP Generate to add and configure cards, generating the next steps in the analysis.
  • How AIP uses Ontology data
• AIP Configure to change pre-existing card configurations by describing how data or a Quiver card should be manipulated.
  • Prompt assumptions

Generate analysis

You can use AIP Generate to generate an analysis from an existing card or data in your analysis through the next actions menu.

To open the AIP Generate dialog, select AIP Generate in the top left menu bar.

Next, select one of AIP's suggestions for object or object set analysis - AIP makes these suggestions based on the properties of the object or object set as well as available Quiver cards that support its use.

Alternatively, input the action you would like to perform next in the query box. AIP will suggest prompt completions as you type.

For best results, be as descriptive as possible. You can try phrasing your prompt in the form of a question such as “How are sales trending over time?” or instead use a directive tone such as “Show me a bar plot of sales revenue over time, grouped by month” or "Show the sum of marketing spend with rows grouped by advertising channel and columns grouped by retailer" for example.

When ready, select Generate.

Using a large language model (LLM), AIP Generate will parse the user’s question to then construct a resulting Quiver graph.

To explore each of the cards closer, you can zoom in and out on the graph and drag the graph around using the mouse scroll gesture or by selecting the buttons on the lower left side.

Hover the cursor on a card to view a helpful explanation for why specific cards were chosen and how the cards were configured in relation to the respective prompt.

To add the resulting graph to the analysis canvas, select Add cards. You can then further modify or finalize the card configuration or visualization of each card.

You can also access AIP Generate's functionality beneath a card containing data or analysis on your Quiver canvas. To insert a prompt, hover over the card and select into the text field to the right of the AIP icon. Verify that AIP's suggestion answers your query and select Add to create an analysis card on your canvas.

How AIP uses Ontology data

To efficiently answer a user prompt, AIP uses only a summarized version of the object set data, or "property value hints", as follows:

• String property types: Up to 100 unique values are computed

• Numeric property types: Min, max, and average are computed

These summaries allow the determination of threshold values when making quantitative descriptions such as high, low, and medium, and also act to correct misspellings of column names and property values.

Configure cards

You can use AIP Configure to update card configurations.

To open the AIP Configure dialog, select the AIP Configure button in the card header.

Next, enter a description for the changes you would like to make to the card, such as “Move the legend to bottom and change style to grouped” or “Change the metric to sum of sales and update the y-axis title to Total Sales".

When ready, select Configure.

AIP Configure will translate these requests to suggested card configuration changes.

If you would like AIP to make additional configurations, then you can input a new description and select Reconfigure. Each suggestion shows the configuration setting that matched to a part of the prompt and can be accepted or rejected individually.

Select Apply to apply the selected changes. The bar plot below shows the result of the accepted suggestions.

You can also access AIP Configure's functionality beneath a card on your Quiver canvas. Hover your cursor over the card and select Modify before entering your configuration prompt into the text field to the right of the AIP icon.

Verify that AIP's suggestion answers your prompt before selecting the suggested modification.

With AIP Configure, everyone can now get that picture-perfect visualization even if they are not familiar with all the visualization settings offered by each Quiver card.

Prompt assumptions

AIP answers prompts that are ambiguous, subjective, or that use relative terms such as "Filter transactions to high spend values" or "Group by the most important customers" by making assumptions. This same mechanism helps it handle spelling mistakes in column names and data values by inferring the correct values from the object set schema and data.

Overall, AIP categorizes card configuration suggestions into either:

• Configuration suggestions, or,
• Configuration suggestions requiring assumptions

Configuration suggestions requiring assumptions will be underlined. You can always hover over the item with your cursor to review the assumption made by AIP.