[acron0]

I'd say that 99% of the problems that 99% of us are solving are not novel, new domains and someone out there has already thought up an ontology for it. He speaker lists some in the talk e.g. FIBO. These are always malleable to whatever use case you need. The win here is being able to enforce adherence to a set of rules that exist at the business level, not the code level. Of course, if your ontology is "wrong" it won't be as effective, but increasingly, those of us who are more like "LLM Product Pilots" than software developers are spending more time having conversations at the ontological level, than the code level.