Skip to content
JustAsk Docs

Building queries & filters with AI

The Workbook Agent enables conversational analytics that take the need for technical know-how out of data analysis.

Workbook Agent

Section titled “Workbook Agent”

The Workbook Agent can help you create and refine workbook queries using natural language. You can ask questions like:

  • What was the total revenue for the last three months?
  • How many new users signed up last month?
  • How many support tickets are submitted on weekends?

The Workbook Agent will either provide a text response or generate a query in the workbook.

Generating queries

Section titled “Generating queries”

In a document draft, click the ✨ (three stars) in the left side navigation. A panel will open next to the field picker with some tips about how to use the feature, as well as a text box to ask your first question.

Workbook Agent panel

In addition to generating queries, the Workbook Agent can also:

  • Iterate on the questions you ask to provide a more refined result. For example:

    You: How many orders did we have in California?
    JustAsk Agent: 1,005
    You: How about in just the last 30 days?
    JustAsk Agent: 126

    Note: Closing the Workbook Agent will delete the text history.

  • Add totals to results, such as adding a column total that sums a Sale Price measure

  • Create new measure fields, such as a Sale Price Average

  • Attach images by pasting from your clipboard to provide visual context (for example, pasting a screenshot of a chart you want to analyze)

    To attach an image, copy it to your clipboard and paste it directly into the Workbook Agent text input. The image appears as a file chip, ready to be sent with your message.

Creating filters

Section titled “Creating filters”

Make filtering easier by having the agent create filters for you using natural language. You can describe a filter like Only include orders created on a Saturday or Exclude customers with a status of deactivated and the agent will automatically apply the filter to the query.

To add an AI filter to your query:

  • Use the Workbook Agent window, or

  • Click the starred funnel icon next to the Options button in the Results tab:

    Workbook AI filter button

Summarizing query results

Section titled “Summarizing query results”

In addition to helping you build queries, the agent can also summarize the results of the query for you. For example, you can ask the agent to:

  • Describe any anomalies in the data
  • Identify insights into trends
  • Detail the next steps you should take

To get started, you can enter a prompt directly in the Workbook Agent or click the chat bubble near the Options button:

Summarize results button

Clicking the Summarize results button will automatically enter a Summarize these results prompt into the Workbook Agent. The agent will typically respond with an overview of the data in the query, some observations, and potential analysis questions:

Query summary from clicking the Summarize results button

View full text response

Hourly Issue Distribution Analysis

Key Insights

  • Peak Hours: Issues are most frequent between 8-14 hours (PT), with a maximum of 1,600 issues at 9 AM
  • Response Time Trends:
    • Fastest median response times (2-3 minutes) occur during 8-16 hours (PT)
    • Slowest response times are late night/early morning (22-23 hours), reaching ~80-97 minutes

Visualization Recommendations

  • What are the busiest hours for issue creation?
  • How does response time correlate with issue volume?

Potential Actions

  • Optimize support staffing during peak hours (8-14 hours)
  • Investigate reasons for slow response times during late night/early morning
  • Consider implementing automated first-response mechanisms during low-staffing periods

If you want to enter an initial prompt that’s more specific, use the Workbook Agent. In the following example, the agent was given the following prompt: Can you please summarize these results and include recommendations for improvement?

Query summary with recommendations

View full text response

Hourly Issue Analysis Summary

Key Insights

  • Peak issue volume occurs between 8-14 hours (PT), with a maximum of 1,600 issues at 9 AM
  • Lowest issue volumes are during late evening/early morning (19-23 hours)
  • Median response times vary significantly across hours

Response Time Observations

  • Best response times (2-3 minutes):
    • 9-12 hours (PT)
    • 14-16 hours (PT)
  • Worst response times:
    • 22-23 hours (PT): ~80-97 minutes median response
    • 18 hours (PT): ~7.7 minutes median response

Recommendations

  • Investigate staffing during peak hours
  • Optimize support coverage for 22-23 hour window
  • Understand why 9 AM has highest issue volume

Potential Action Items

  • Adjust support team scheduling
  • Implement automated first-response mechanisms
  • Analyze root causes of high-volume periods

To make a summary part of a dashboard, use the AI summary visualization.

Generating forecasts

Section titled “Generating forecasts”

The agent can generate statistical forecasts for time-series data. Refer to Generating forecasts with AI to learn more.

Generating visualizations

Section titled “Generating visualizations”

The agent can also generate visualizations based on your query results. Refer to Generating visualizations with AI to learn more.

Getting help

If you’re stuck and can’t remember how to do something in JustAsk, just ask the JustAsk Agent. Questions like “How do I do [thing]?” will prompt the agent to search the docs and provide you with an answer, all without leaving your JustAsk workflow.

You can also directly tell the agent to search the docs when researching the answer to your question.