Before and After Comparison Design AI Prompt

Design a visualization that effectively communicates before-and-after comparison.

Scenario: {{scenario}} (policy change, product launch, intervention, etc.)
Before period: {{before}}
After period: {{after}}
Metric: {{metric}}

1. Chart options for before/after:

   Slope chart (most effective for 2-point comparison):
   - Two vertical axes (Before | After)
   - Each entity is a line connecting its before value to its after value
   - Lines going up = improved, lines going down = declined
   - Color-code by direction: green for improvement, red for decline, grey for neutral
   - Best for: comparing many entities before/after a single event

   Paired bar chart:
   - Two bars per entity (before in grey, after in color)
   - Sort by the change magnitude (largest improvement first)
   - Add a difference annotation between each pair
   - Best for: few entities with absolute value comparison needed

   Dumbbell chart:
   - A horizontal dot plot variant
   - One dot for before, one dot for after, connected by a line
   - Dot size can encode a third variable (e.g. sample size)
   - Best for: clean, minimal presentation of many entities

   Difference area chart:
   - Two lines (before and after) with the area between them shaded
   - Green shading where after > before, red shading where after < before
   - Best for: showing the cumulative effect over time

   Bump chart:
   - Showing rank changes rather than absolute changes
   - Lines connecting before-rank to after-rank for each entity
   - Best for: rankings, leaderboards, or relative position changes

2. Choosing the right chart:
   - 2 entities: paired bar or slope chart
   - 3–10 entities: slope chart or dumbbell
   - > 10 entities: dumbbell or filtered slope (highlight top/bottom movers)
   - Rank focus: bump chart
   - Time series with intervention line: annotated line chart with shaded 'after' region

3. Statistical context:
   - Is the before-after difference statistically significant?
   - Add error bars or confidence intervals where sample sizes are small
   - Label the change magnitude on the chart (not just the before and after values)

4. Intervention line:
   - On a time series: mark the exact intervention date with a vertical dashed line
   - Label the line: 'Campaign launch (Mar 15)'
   - Shade the before period lightly grey, the after period white

Return: recommended chart type with rationale, design specification, and statistical context requirements.