Data products promise decentralised ownership, faster delivery, and business-aligned analytics. For a time, that promise largely held. But with the arrival of AI, a fault line has become impossible to ignore: the business speaks in terms of customers, risk exposure, and supplychain disruptions, while classic data products speak in tables, columns, and schemas. Somewhere between those two worlds, meaning is lost – and with it, much of the value for AI. This is not a data problem. It is a meaning problem. In this hands-on workshop, participants will build semantic data products step by step using the Data Product Ontology (DPROD) and an Enterprise Information Architecture (EIA). The core pattern is simple and repeatable: each data product explicitly maps its output schema to a Business Object in a shared ontology. This single modelling step transforms data products from isolated technical artefacts into discoverable, governable, and reusable business assets - usable by both humans and AI systems. Working in metaphactory with pre-configured datasets, participants will: As the workshop progresses, participants will see how ontology can become a semantic entry point to the organisation's data landscape. The workshop concludes with a live, business-facing demonstration showing how users and AI agents can discover and navigate data through business language rather than technical schemas, assess downstream impact, and reason over the data product landscape.