Ontologies should be integrated into agent loops as validators after tool execution: tool results are formatted according to the ontology, and a reasoner checks whether the response is valid before accepting or rejecting it.

normativepending

Speaker

Frank Coyle

Evidence Quote

“The tool's going to give us information. We put the information in a form that our our our our validator can use, and think about the validator as operating with this these ontologies about our domain, then we can make some sense of whether the response of the LLM is reasonable.”

Source

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley— AI Engineer
Created: 8/12/2026, 5:57:54 PM

Your notes

Loading notes...