One AI Assistant Visualizations

Overview

One AI Assistant Visualizations lets you create charts, tables, and key values from your people data using natural language prompts. Ask for “headcount” or “hires and exits by department over the past 12 months with a forecast,” and the assistant will automatically generate the best visualization—whether that’s a bar chart, spline, table, scatterplot, or single value.

You can refine the results by adjusting filters, switching chart types, customizing formatting, or adding features like forecasts, reference lines, and annotations. When you're ready to share or revisit your work, you can pin it to a Storyboard, save it to the Insights Library, or export it.

What You Can Do With Visualizations 

• Generate charts, tables, and key values from natural language prompts. The assistant automatically selects a visualization type based on the shape of your data and the structure of your prompt.
  • Supported types include bar, spline, line, area, area spline, scatterplot, geomap, table, and single value
  • A metric by a dimension defaults to a bar chart
  • A time series defaults to a spline chart
  • A single metric by a geospatial dimension defaults to a geomap
  • Example: "headcount by location as an area spline chart"
• Display multiple metrics and dimensions at once. You can include several measures and breakdowns in a single prompt.
  • Example: "hires, exits, and headcount by department and gender"
• Apply time selections with flexible phrasing. Use general terms to specify fixed or rolling periods or time models.
  • Past X months/quarters/years can be requested, even if not available as a time model
  • Examples: "July 2024", "Q1 of 2023", "past 17 days", "last 6 months"
  • Currently, only the default calendar on your site is used
  • Year, Quarter, Month, and Day are the levels available; weeks are not currently supported
  • Past and Future time is not currently supported
  • Calendar selections work best when you use general time references like years, quarters, months, or specific dates. While custom labels such as “FY 2024” or “CY25 Q1” may sometimes work, results are more consistent when using standard terms like “2024” or “Q1.”
• Filter results by dimensions or specific values. Include or exclude values directly in your prompt.
  • Examples: "excluding contractors", "only full-time employees", "just finance and HR"
  • You can also target specific dimension levels or nodes
  • Examples: "Sup Org L3", "Talent Acquisition"
• Sort, rank, and limit results using natural superlatives. Ask for top or bottom results in plain language.
  • Most, least, highest, and lowest are good words to use to get these results
  • If no number is provided, five results are shown by default
  • Sorted charts default to horizontal bars
  • Examples: "top 3 job families by terminations", "top recruiters for time to fill last year?"
• Drill Through into the data behind any point. Click on a chart element or table value to see the underlying records.
  • Drill Through behavior follows your site’s configuration
• Add forecasts. Forecasts can be included directly in your prompt or configured in the Discover tab of the query panel.
  • Forecast periods default to four unless otherwise specified in the prompt or adjusted in the Discover tab
  • Additional forecast settings—such as forecaster type and confidence interval—can be edited in the Discover tab
  • Example: "headcount over the last 12 months with a 3-month forecast"
• Customize every part of the chart or table. Use the Define, Design, Discover, and Describe tabs to make edits.
  • Modify metrics, dimensions, filters, chart type, sorting, styling, and formatting
  • Add annotations or enable Embedded Insights such as lines of best fit and reference lines
• Export, pin, or save your results. Download or save your output for future use or sharing.
  • Export as an image or CSV
  • Pin to an existing Storyboard, create a new one, or save to the Insights Library
• Provide feedback on the result. Use the thumbs up or thumbs down buttons below the visualization to let the assistant know whether the result was accurate.
  • If you select thumbs down, you’ll have the option to include a comment
  • Feedback is reviewed by the One Model team to help improve the assistant

How Visualizations Works

When a prompt is submitted, One AI Assistant uses OpenAI’s large language model (LLM) to identify essential elements, such as metrics, dimensions, dimension nodes, and time selections within the prompt. For instance: 

• Headcount is a metric
• Cost Center is a dimension
• Brisbane is a dimension node
• Last 12 months is a time selection

These recognized elements are then sent back to One Model, where One AI Assistant queries a vector database to find the closest matches in your data. Dimension nodes (e.g., “Engineering” within Cost Center) are also available in this process, allowing for specific filtering requests, such as “Show me headcount for the Engineering department only.”

Only data configured and permissioned for the assistant’s use during setup can be accessed, matched, and used in analysis. If a metric or dimension name was not embedded, it won’t be included in the assistant’s analysis, nor will it be shared with OpenAI.

With the matched metric(s), dimension(s), and time selection(s), One Model generates a query based on your request through its query engine. One AI Assistant then presents the data in the optimal or requested format, whether that’s a table, chart, or key value. Using the query panel, users can see and modify the metrics, dimensions, time selections, and filters that were used to construct the data visualization.

Creating and Interacting with Visualizations

One AI Assistant can be accessed from the prompt input bar at the top of any page in One Model. Creating a visualization with One AI Assistant is as simple as typing a prompt and reviewing the result.

1. Accessing One AI Assistant and the Initial Prompt
   • Enter a clear, concise prompt and click Go or press Enter.
   • If configured for your site, you can also expand the dropdown to browse example prompts.
   • The assistant uses generative AI to identify metrics, dimensions, dimension levels, time selections, filters, sorting, and forecasting instructions in your prompt and generates a data visualization based on those inputs.
   • Example: “Show me external hires and terminations for the past 8 quarters”
   • If One AI Assistant Answers is also enabled, the assistant will first check for a matching admin-approved chart. If one is found, that chart will be returned. If not, a new visualization will be generated based on your prompt.
   • Refer to the Prompting Best Practices section below for guidance.

One AI Assistant prompt bar

One AI Assistant example prompts

One AI Assistant expanded view

2.  Using Visualization Mode

   • In AI Mode, the Assistant tries to return the most useful response for your prompt. Because results depend on your organization’s configuration and permissions, it may not always produce a visualization when you expect one. To guarantee the creation of a chart, table, or value, switch to Visualization Mode before entering your prompt. Every request will then generate a visualization directly.

   • 
3. Interacting With the Data
   • Just like Storyboards in One Model, the results displayed in One AI Assistant are interactive.
     1. Hovering over a data point reveals additional information.
     2. Clicking a series in the legend hides or reveals that series.
     3. You can switch to a table view at any time.
     4. Drill Through to detail is available by clicking on a data point.
4. Modifying Your Prompt
   • To adjust your result, simply edit or replace the original prompt text above the visualization and click Go or press Enter.
5. Modifying the Query
   • One AI Assistant includes a full query builder that allows you to adjust the result without rewriting your prompt. The Define tab in One AI Assistant shows how your prompt was interpreted and lets you refine it without retyping. You can update metrics, dimensions, chart types, filters, and more.
     1. Choose a visualization type: Select from Basic Chart, Table, or Key Value. Please note that several chart types fall under the Basic Chart option. These can be defined for each metric as explained in the next bullet.
     2. Add or adjust metrics: Use the + button to add metrics or the x to remove them. You can mix multiple metrics in the same chart or table.
        • Click a metric chip to:
          • Select a series type (spline, column, line, area, area spline)
          • Toggle horizontal bar layout
          • Enable Top/Bottom filtering and define the count
          • Apply sorting (ascending or descending)
     3. Add or adjust dimensions: Use the + button to add dimensions or the x to remove them.
        • Click a dimension chip to:
          • Pivot to X-axis
          • Include or exclude specific levels or nodes
          • Review selected values and clear them using Clear All
          • Control dimension nodes
        • Dimension node selection icons indicate:
          • The eyeball icon indicates selection of a node.
          • The checkmark icon indicates inclusion of a node.
          • The X icon indicated exclusion of a node.
          • Clicking the right arrow if one is displayed expands that node of the dimension to display nodes included at the next level.
        • Pivoted dimensions appear on the X-axis in charts and as columns in tables. All other settings (like selections, filters, and levels) work the same as standard dimensions.
     4. Use time models: They’re available for time dimensions and enable dynamic selections that update automatically as time progresses. For example, if you select Today, it will always reflect the current date each time the site is processed.
     5. Pivot columns from your data model: Use them to include raw columns from your fact or dimension tables. These behave like pivoted dimensions in the output.
   • Once all changes are made, click Run Query to regenerate the visualization with your updated selections.
6. Design | Discover | Describe
   • In addition to the Define tab, three additional tabs allow you to refine and enhance with a number of visualization settings:
     1. Design – Change the appearance of your visualizations using layout, formatting, and styling options.
     2. Discover – Configure One AI Embedded Insights, which apply statistical analysis directly to tiles—enhancing your people data with derived insights.
     3. Describe – Add or edit annotations on basic charts to make your visuals more informative, contextual, and accessible.
7. Exporting and Pinning Results
   • You can save and share your visual directly from One AI Assistant.
     1. Export Chart: Download a PNG image of the chart (Basic Charts only at this time)
     2. Export Data: Download a CSV of the underlying data
     3. Pin to your Insight Library, a new Storyboard, or an existing Storyboard 

Example Prompt Patterns

These example prompts show the kinds of inputs One AI Assistant can interpret. Replace the bracketed terms with your actual metric names, dimension names, and time selections.

• [metric name]
  → headcount
• [metric name] and [metric name]
  → hires and exits
• [metric name] for [time selection]
  → headcount for July 2025
• [metric name] by [dimension]
  → hires by department
• [metric name] by [dimension] for [time selection]
  → terminations by location over the past 12 months
• [metric name] for [dimension selection]
  → headcount for finance and HR
• top/bottom/highest/lowest [dimension] for [metric name]
  → top departments for turnover rate
• top/bottom/highest/lowest [number] [dimension] for [metric name]
  → bottom 3 locations for promotions
• forecast [metric name]
  → forecast headcount
• [metric name] for [time selection] with a [number]-period forecast
  → headcount over the past 12 months with a 3-month forecast
• [metric name] and [metric name] by [dimension] on a scatter plot
  → salary and performance rating by manager on a scatter plot

Prompting Best Practices

Since the assistant relies on a large language model (LLM) and a vector database to interpret prompts and match them with your data, using clear, deliberate prompts helps ensure accurate results. Here are some best practices to keep in mind:

• Be specific, yet concise. Clearly state the metrics and dimensions you want to analyze. Avoid vague requests like "show performance" and instead ask for "show headcount for the last 12 months by department". While specificity is important, avoid overloading your prompt with unnecessary detail. Clear, concise prompts are easier for the LLM to interpret correctly.
• Dimension levels. If you know the specific level of a dimension you want, include it in your prompt (e.g., "terminations for the last 5 years by sup org L3"). Otherwise, the assistant defaults to level 1, and you'll need to manually adjust the level in the query panel.
• Describe calendar selections generally. For calendar terms, general descriptions work better than customized formats. Use "2025", "Q3 of 2024", "Jan 2024", or "2020-01-12" instead of custom calendar labels like "FY 2024" or "CY25 Q1". Custom labels aren't searchable by the assistant, so results can be inconsistent. One AI Assistant currently references only your site’s default time dimension.
• Use familiar terms. While the vector database understands common synonyms, using terms that match those in your data improves accuracy. For example, prompt with "location" instead of "office site" if that’s how the field is labeled in your data.
• Avoid ambiguity. If there are similarly named fields—like "work location" and "home location"—be specific in your prompt to avoid misinterpretation. Avoid terms that could apply to multiple fields when possible.
  • The One AI team is developing a feature that will allow site administrators to prioritize which metrics or dimensions are returned for common prompt terms. For example, if your site includes multiple "Headcount (EOP)" metrics, admins will be able to control which version is returned when users simply prompt "headcount".
• Include context. To narrow results, add context like time periods ("last quarter", "past year") and organizational units ("finance team", "sales department").
• Refine as needed. If the result isn’t what you expected, rephrase the prompt or add more detail. If you have drill-through access, use it to inspect the metric definition and confirm the assistant selected the correct one.

Conclusion

One AI Assistant Visualizations makes it fast and intuitive to generate meaningful charts, tables, and values directly from your data using natural language. With flexible prompting, built-in customization, and seamless access to forecasting and insights, it brings the full power of One Model’s visualization engine to your fingertips—no advanced configuration required.