Why Agentic Systems Need Ontologies

I came across this today. Watching it hit that itch of something I kinda do already. It also ties to how Jake's looking to the past to guides how things work with LLM. The second brain, how things are linked, etc.

Just sharing as something that may help people think about LLM in tools and such. I'll leave it with to quotes from the description and the talk.

"Nothing is a mistake.

There is no win, no fail.

Only MAKE."

" An ontology is just typed entities, relationships, and constraints, expressed with old and boring standards like RDFS and OWL, that let you say a payment status must be one of three values, that a customer and a support rep are different things, that an order can only be refunded once. Wrap a Claude tool use loop with a validator: when the model proposes a tool call, check its types with Pydantic and its results against the ontology, and only then let it act. The catches that are painful to write in English become a few lines of logic."

6 comments

Why Agentic Systems Need Ontologies