1. Home
  2. Guides
  3. Concepts
  4. Tools
  5. References
    1. Apache Spark
    2. Built-in Functions
    3. Incorta Component SDK
    4. Incorta Connector SDK
    5. Connectors
    6. Copilot
      1. Setup
      2. Audit Dashboard
      3. Business Assistant
        1. Insight Generation
        2. Clustering
        3. Forecasting
        4. Key Driver Analysis
        5. Tree Decomposition
      4. Story Telling
    7. Data Studio
    8. Public API
    9. Security
    10. SQL Interface
    11. Visualizations
    12. Other
  6. Integrations
  7. Data applications
  8. Release Notes
  9. Incorta Premium

Incorta Copilot Insight Generation

The Incorta Copilot feature enables users to create interactive visualizations through natural language prompts. This document explains how to use Copilot to generate insights, edit them, and understand the underlying data.

Using the /insight command

To generate a visualization:

  • Type /insight followed by your prompt
    • Example: /insight calculate the composition of lifestyle segment across my customers
  • Press Enter or click the send button (arrow icon)

Understanding generated Insights

When Copilot processes your request, it:

  • Interprets your natural language prompt
  • Identifies relevant dimensions and measures
  • Selects the appropriate visualization type
  • Creates and displays the visualization with a descriptive title

Accessing the Insight editor

To modify a generated insight:

  • Click the Open icon in the top-right corner of the insight
  • This opens the Insight in the Analyzer interface

Saving the Insights

After creating or editing an insight:

  1. Click the "Save" button in the top-right corner
  2. Select a dashboard to add the insight to

Examining the Result Set

Underlying every insight is a Spark SQL result set. To view, open Manage Dataset, go to the Result Set tab, and select the pencil icon of the SQL result set. This SQL can be directly edited.

Best practices for Copilot Insights

  • Be specific in your prompts: "Calculate the composition of lifestyle segment" is better than "Show me customer data"
  • Reference column names: Use column terminology that matches your data model
  • Start simple, then refine: Begin with basic insights, then use the editor to customize
  • Examine the result set: Understanding the underlying data helps create more meaningful insights
  • Iterative refinement: If the initial insight isn't exactly what you need, refine your prompt or use the editor
  • Explicit directions: If you desire a specific insight type for visualization, mention it in your prompt.