A/B: Heatmaps & Recordings

Go beyond “Variant B has +X% lift.” Use heatmaps and recordings by variant to explain why a variant won — and what to ship next.

Variant heatmap comparison
Screenshot placeholder
1200×650px • /docs-images/ab-testing/variant-heatmaps-1200x650.png
Add a file at this path to replace the placeholder.
Screenshot to add: variant comparison heatmaps (side-by-side or toggle) with metric deltas.

Trust checks first

Before you believe the result, check:

  • SRM (Sample Ratio Mismatch): traffic split matches what you configured.
  • Delivery health: variants are actually applying on the page (selectors found, apply success rate).
  • Dedupe: visitors aren’t double-counted on refreshes or thank-you reloads.

Why delivery health matters

A test can “look good” if the variant fails to apply for a large fraction of visitors. Always check delivery health before shipping the winner.

Explain a win with heatmaps

  1. Open the tested page’s heatmap.
  2. Enable Compare variants and select Control vs Variant.
  3. Use the difference overlay to see where clicks increased or decreased.
  4. Check scroll depth differences (did Variant push key content above the fold?).

Prove the “why” with recordings

Heatmaps show aggregate behavior. Recordings show the story: hesitation, rage clicks, navigation loops, and whether people noticed the change.

Watch examples from heatmap
Screenshot placeholder
1200×650px • /docs-images/ab-testing/watch-examples-1200x650.png
Add a file at this path to replace the placeholder.
Screenshot to add: 'Watch examples' link from heatmap leading to sessions filtered by test and variant.
  1. From a heatmap hotspot/dead zone, click Watch examples.
  2. Filter sessions by test and variant.
  3. Watch 5–10 sessions per variant to confirm the mechanism of change.

What to do next (decision checklist)

  • If the variant wins and trust checks are clean: ship it (or run a follow-up test).
  • If the variant loses: inspect recordings for confusion, broken selectors, or mobile regression.
  • If there’s no winner: adjust hypothesis, increase traffic, or pick a larger-change variant.

Related: Heatmap segmentation and reviewing sessions.