Score the engagement, live
Load one of the example personas or move the factors yourself. The score, the band and the factor breakdown recompute instantly, and the recommended play follows the band. Note what is missing: spend never enters the read.
Factors
How often they show up, independent of spend (1 = rarely, 5 = constantly)
Distinct products and features used (1 = single, 5 = broad)
How fresh their last active session is (1 = long silent, 5 = active now)
Engagement read
- +40Session rate. How often they show up, independent of what they spend
- +23Feature depth. How much of the product they actually use, not just how much they buy
- +20Recent activity. How fresh their last active session is, the early-warning half of the signal
A power customer: they show up constantly and use the product broadly. Reward the habit and turn it outward, with early access, recognition, a reason to bring others in.
Illustrative and explainable: the score is the sum of named factors, held apart from spend, so you always see the why. The production model runs in the warehouse and pushes the score into Braze.
That is Engagement Score working on sample data. The service page has the rest: what it needs from you, how long it takes to build, what it pairs with, and how the lift gets proven.