One engine. Many catalogs.
Every demo below runs on the same engine: the taste graph, a vertical ontology, the metadata schema, the multimodal stack, the evaluation harness. Only the catalog changes.
Star Tribune food and event discovery
Consumer discovery across the Minnesota Star Tribune's food and event coverage. A paid deployment, delivered on time and on scope, and run live at an 11-day public event.
Movie and TV discovery
Taste-first discovery across a film and television catalog. Learns preference by contrast on day one. No viewing history required.
Enterprise and editorial knowledge search
Semantic search across an editorial archive, matched on meaning.
Retail discovery
A product catalog, matched on meaning and taste.
Resale discovery
One-of-a-kind inventory, where no two listings share a title.
Cultural collection
A collection catalog, explorable in natural language.
Contact
See it on your catalog.
The fastest way to evaluate the engine is a working demo on your own catalog. Tell us what your audience cannot find.