What-If Analysis Skill

This skill compares projected metric values under different business assumptions by creating alternative MAQL calculations and showing the results side by side.

How It Works

The What-If Analysis skill compares projected metric values under different business assumptions by creating alternative MAQL calculations. When activated, the assistant:

1. Identifies the base metric and the variable to change
2. Creates scenario metrics with different MAQL expressions (e.g., Revenue × 0.9, Revenue × 0.8)
3. Uses the Visualization skill to compare scenarios side by side
4. With data sharing enabled, interprets results and provides recommendations
5. Shows comparisons in a single visualization for easy analysis

The skill helps you understand the impact of different business decisions by modeling alternative scenarios and comparing their projected outcomes. Scenarios must be expressible as metric formulas using arithmetic operations.

Examples

Comparing Discount Scenarios
The user asks: What if we discount by 10% vs 20%?
The AI Assistant then:

• creates scenario metrics (for example, Revenue × 0.9 and Revenue × 0.8),
• compares them in a single visualization, and
• summarizes the difference.

Modeling Growth Assumptions
The user asks: Compare revenue if customer growth is 10% vs 15%.
The AI Assistant then:

• creates scenario metrics with different growth rates,
• visualizes the comparison, and
• explains the impact.

Analyzing Cost Changes
The user asks: What happens to profit if we reduce costs by 20%?
The AI Assistant then:

• creates a scenario with an adjusted cost calculation,
• compares the profit outcomes, and
• summarizes what changes.

More Example Prompts

• Compare revenue if we increase prices by 5% or 10%.
• Show me revenue under different cost scenarios.
• Compare sales if we add a new region.

Limitations

• Requires the Visualization skill as a dependency
• Scenarios must be expressible as metric formulas (arithmetic operations)
• Base metric must exist or be created first
• Results interpretation requires data sharing to be enabled (when disabled, provides visualization only)
• Complex scenarios may require multiple metric dependencies
• Users need permission to create metrics for scenario metrics