Visualization Skill

Create charts, tables, and visualizations from metrics and dimensions. Analyze data visually and find insights. This skill is foundational—many other skills depend on it to display their results.

Experimental Feature

This is an experimental feature that is still under active development. Its behavior may change in future releases, or the feature may be removed.

How It Works

The Visualization skill creates and executes visualizations from your analytics data. When activated, the assistant:

  1. Creates ad-hoc visualizations using metrics and dimensions
  2. Validates visualization definitions before execution
  3. Executes visualizations to retrieve data for analysis (when data sharing enabled)
  4. Searches for attribute values across labels
  5. Displays results as charts, tables, or other visual formats

The skill supports the following visualization types: TABLE, BAR, LINE, PIE, COLUMN, HEADLINE, and SCATTER. It can work with any metrics and attributes in your workspace. It’s used by other skills to display their results, making it a core dependency for most analytical capabilities.

Examples

Creating a chart:

User: "Show me revenue by region"
Assistant: [Creates bar chart with Revenue metric and Region attribute, executes, displays]

Visualizing analysis:

User: "Visualize the forecast for next quarter"
Assistant: [Uses forecasting results, creates line chart with historical and forecasted data]

Exploring data:

User: "Create a table showing sales by product and month"
Assistant: [Creates pivot table, executes, displays data]

Other use cases:

  • “Create a bar chart of sales by product”
  • “Visualize the forecast results”
  • “Show the clusters in a chart”
  • “Create a table of customer metrics”
  • “Show me a line chart over time”

Limitations

  • Visualization creation requires appropriate workspace permissions
  • Chart types depend on available metrics and dimensions
  • Data sharing must be enabled for the AI Assistant to analyze visualization results and provide summaries (when disabled, visualizations are still created and displayed, but the assistant cannot access the data)
  • Some complex visualizations may require specific metric/attribute combinations
  • Attribute value search works across labels but may have limitations with very large attribute sets
Metric Skill
What-If Analysis Skill