Ground – Beyond the lakehouse: the ontology as the data layer AI & humans can actually use

Part 5 of the Sovereign AI series, for CDOs, heads of data and analytics, and data architects — in any sector. The lakehouse gave you governed storage on open formats: table-shaped, read by analysts. Agents, and increasingly analysts, reason over meaning — entities, relationships, state and rules that people, applications and AI read from and write back to. That is an operational ontology, and it is not a semantic layer or a knowledge graph. Live: the same business question answered by vector RAG over documents and by ontology RAG over the model, side by side with provenance; then an agent writing back through the ontology to an operational system under policy. And the migration path from an existing lakehouse — what you keep, what you add, what you never move.

Speaking:

Ping Xavier

Ping Nathan

Language: English

Agenda

11:00 - Why "AI-ready data" turned out to mean something other than clean tables (Nathan)

11:05 - Lakehouse, semantic layer, knowledge graph, ontology — one slide, four definitions

11:12 - Live (Xavier): the same question through vector RAG and through ontology RAG, with provenance

11:22 - Live: an agent writes back through the ontology to an operational system, under policy

11:30 - The migration path from your lakehouse: what you keep, what you add, what you never move

11:37 - Q&A