Intent vs propensity
Intent is what a customer is doing in this session; propensity is a model's prediction of how likely they are to take an action, learned from history. One is observed and current, the other is predicted and trained, and they answer different questions.
Two different questions
Intent asks what a customer is doing right now. Propensity asks how likely they are to do something, based on what customers like them have done before. The first is about this session; the second is about a population and a pattern. They are often confused because both get used to decide what to show a visitor, but they start from different places.
Observed versus predicted
Intent is observed: the evidence is the behavior in front of you, current as of this click. Propensity is predicted: the evidence is a trained model and the features it reads. Observed intent needs the live state of the session. Predicted propensity needs labeled history, a feature pipeline and a model kept in step with production.
When each fits
Propensity fits when you want a ranked probability across many customers and you have the history to learn it. Intent fits when you need to act on what is happening in the session, while the customer is still on the page. Many teams want the second and reach for the first, because propensity is the path they know, and the project stalls on the data science before it ships.
See it on your own traffic
Add the SDK, define one attribute, and see an attribute updating against your own traffic in the first session. The free tier runs on the real engine: no card, no sales call.