Frank Coyle

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

ontology design for AI agents23. Juli 2026

Ontologies as formal shared conceptualizations

Frank Coyle defines an ontology as a formal specification of a shared conceptualization and says agents should be given that conceptualization of their domain.

Stützende Belege

Frank Coyle·23. Juli 2026

Originalauszug

It is a, a formal specification of a shared conceptualization, and that's what we wanna give to our agents. We wanna give them our concept-- our conceptualization of the universe, our universe, our domains.

Kontext

knowledge and, uh, graph technology really represents.

Original öffnen · 3:45 Transkriptquelle

Die Startzeit stammt aus dem bereitgestellten Transkript. Die Synchronisierung der Wiedergabe steht noch zur Überprüfung an.

neurosymbolic AI architecture

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

neurosymbolic AI architecture23. Juli 2026

Neurosymbolic AI as LLM guardrails

Frank Coyle argues that neurosymbolic AI can help keep probabilistic LLMs on guardrails.

Stützende Belege

Frank Coyle·23. Juli 2026

Originalauszug

what I'd like to argue is that neurosymbolic AI sort of represents a way to keep the LLM on its guardrails, because LLMs are by nature probabilistic.

Kontext

And so

Original öffnen · 4:46 Transkriptquelle

Die Startzeit stammt aus dem bereitgestellten Transkript. Die Synchronisierung der Wiedergabe steht noch zur Überprüfung an.

agent validation workflow

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

agent validation workflow23. Juli 2026

Ontology-driven validation in agent loops

Frank Coyle proposes using ontologies after a tool runs, formatting the returned information for a validator that operates with domain ontologies.

Stützende Belege

Frank Coyle·23. Juli 2026

Originalauszug

if you look down there, a-after the, the tool is called, it said, "Tool runs," this is where ontologies could come in. The tool's gonna give us information. We put the information in a form that our, our, our, our validator can use.

Original öffnen · 16:45 Transkriptquelle

Die Startzeit stammt aus dem bereitgestellten Transkript. Die Synchronisierung der Wiedergabe steht noch zur Überprüfung an.

ontology-based business logic enforcement

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

ontology-based business logic enforcement23. Juli 2026

Ontologies for catching domain-specific errors

Frank Coyle says ontologies could catch errors such as a second refund on one order or a payout sent to support instead of the buyer. He describes catching such errors in English as tricky.

Stützende Belege

Frank Coyle·23. Juli 2026

Originalauszug

A second refund on the same order is a, is, is a problem. [laughs] Ontologies could catch it, whereas it's ver- it's very tricky to do that in, in English. A payout sent to the support desk instead of the buyer, okay?

Original öffnen · 19:12 Transkriptquelle

Die Startzeit stammt aus dem bereitgestellten Transkript. Die Synchronisierung der Wiedergabe steht noch zur Überprüfung an.