Generative UI vs server-driven UI
Server-driven UI and generative UI both move layout decisions to the server. The difference is what drives the decision. Server-driven UI picks from a fixed set of components, while generative UI chooses based on live data about the visit.
Server-driven UI
In a server-driven UI, the server returns a description of the screen and the client renders it from a component library it already ships. It decouples releases: you can change a screen without shipping a new app build. What the server returns is still usually the same for everyone in a given state.
Generative UI
Generative UI keeps that server-decides model and adds the input that makes it per-visit: data about who is looking and what they are doing. The server does not just pick a known screen. It composes one for the request from that data and a set of rules or a model.
How they relate
Server-driven UI is the delivery mechanism. Generative UI is what you do with it once the decision is informed by live state. Most teams that want generative UI build it on top of server-driven UI.
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.