Using an AI visual

Interacting with the AI visual

Once the AI visual is configured, you can begin exploring your data through conversational queries. You can ask questions about your data using voice or text. The AI visual generates responses based on the connected dataset, making it easy to gain insights using natural language. The AI visual uses the configured approach to generate responses that directly reference the underlying dataset.

• Text input: Type your question into the input field and click SEND to submit the query. The AI visual processes your question and returns a relevant response based on the dataset.

• Speech input: Click to ask a question using your voice. Your speech is converted to text and entered into the input field. Click SEND to submit the query.

• Follow-up queries: Continue the conversation by asking follow-up questions, refining or extending your original query, using either voice or text input.

Viewing response details

You can view detailed information about how the AI visual generated a response. Execution details provide a transparent, step-by-step view of how the AI visual generated the response. This summary can help you understand exactly how your queries are processed and the data used in the analysis or to confirm that data sources, filters, and calculations are accurate before making decisions based on the output.

You can also use it for debugging purposes, to identify where a query or analysis may have produced unexpected results.

To view the response generation details, click next to the reply. The Execution Details modal shows:

• Overview – Summary information of AI approach, completion profile, dataset details, filters applied, steps and duration of execution, response length, and the original question.

• Execution Steps – A breakdown of how the response was generated

  • Checking Previous Data – determines whether earlier queries already contain the needed information
  • Collecting Dataset Information and Filters – shows dataset details and applied dashboard filters
  • Generating SQL – shows the generated query and visual configuration
  • Executing Query – shows the query execution results
  • Analyzing Results – provides the natural language summary of the query results

You can expand each step to view the associated data, dataset information, filters, or query results.

To keep a copy of the execution details, click Download.

Sharing parameters

When using an AI visual to query the underlying dataset, the generated parameters can be shared with other visuals on the dashboard to enable cross-filtering.

Sharing parameters allows you to explore relationships between different data points quickly. When you change a shared parameter, all dependent visuals on the dashboard update automatically. This feature helps synchronize multiple visuals to reflect the same subset of data, eliminating the need to adjust each visual manually. By applying the same filter across multiple visuals at once, sharing parameters saves time and ensures consistency, making it easier to analyze and compare related data points.

1. Open the Share Parameters modal by clicking next to the reply.

   The dialog lists available parameters. Each parameter shows column and values information.

2. Select the parameters you want to share.

   You can use Select All or Select None if multiple parameters are available.

3. [Optional] Include null values.

   Enable the toggle if you want null or empty results from the AI query included in the shared parameters, allowing other visuals to filter for missing or empty data.

4. Click SHARE PARAMETERS to apply parameter sharing.

   You can click Cancel if needed to close the dialog without making changes.