Attribution & proof

Most tools tell you what they touched. Sarah tells you what she changed. Her revenue is measured against a control group that never saw her, so the number is lift you can trust.

The problem

When an assistant gets credit for every order it brushed against, the dashboard reads great and means little. You can't tell the sales she caused from the sales that would have happened anyway. Without a control, attribution is a story, not a measurement.

How it works

• Multi-touch journey. Every order is traced from the first widget touch through to purchase, so the full path is on record, not just the last click.
• Five attribution models. The same journey is scored five ways: last-widget, linear, time-decay, first-touch, and position-based (U-shaped). You pick the lens that fits how you think about credit.
• A 30-day window. Touches count for 30 days, built deliberately long for slower gifting and jewelry cycles where the decision takes weeks.
• An A/B holdout. A percentage of visitors never see Sarah. Their order rate is the control. Her lift is measured against them, so the headline is incremental revenue, not assumed credit.

What makes it real

Ten distinct touch types are tracked across the journey, and attribution is computed at order time against the recorded path. The holdout is the honest part: because a real slice of traffic is held back as a control, the revenue figure reflects causation, not correlation. A note on scope: the holdout is opt-in and set up by you, and the email and SMS touch types are framework-only today, not yet wired into the live measurement.

Pairs with Campaigns and Outbound & webhooks.