Taste Graph
What is Taste Graph?
The Taste Graph is a structured representation of taste and affinity that makes human taste computable, so AI systems can reason about what a person will find resonant rather than merely relevant.
Most systems treat preference as a byproduct of behavior. Someone clicks, buys, or lingers, and the system infers what to show next. That works until the history is thin, the catalog is new, or the person is here for the first time. The Taste Graph starts somewhere else. It represents taste itself as structure, so a system can reason about what a person will find resonant before it has watched them act.
In practice, the Taste Graph places people and content on shared, grounded scales of perception rather than in coarse buckets. That lets an AI product ask a sharper question than what is popular or what is similar. It can ask what this specific person will find resonant, and act on the answer at inference, without storing personal data. Reranking, customer intelligence, and agent context all read from this same representation.
Updated July 11, 2026