Frank Coyle

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

ontology design for AI agents23 jul 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.

Evidencia a favor

Frank Coyle·23 jul 2026

Extracto original

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.

Contexto

knowledge and, uh, graph technology really represents.

Abrir el original · 3:45 Fuente de la transcripción

La hora de inicio proviene de la transcripción proporcionada. La alineación de la reproducción está pendiente de revisión.

neurosymbolic AI architecture

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

neurosymbolic AI architecture23 jul 2026

Neurosymbolic AI as LLM guardrails

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

Evidencia a favor

Frank Coyle·23 jul 2026

Extracto original

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.

Contexto

And so

Abrir el original · 4:46 Fuente de la transcripción

La hora de inicio proviene de la transcripción proporcionada. La alineación de la reproducción está pendiente de revisión.

agent validation workflow

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

agent validation workflow23 jul 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.

Evidencia a favor

Frank Coyle·23 jul 2026

Extracto original

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.

Abrir el original · 16:45 Fuente de la transcripción

La hora de inicio proviene de la transcripción proporcionada. La alineación de la reproducción está pendiente de revisión.

ontology-based business logic enforcement

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

ontology-based business logic enforcement23 jul 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.

Evidencia a favor

Frank Coyle·23 jul 2026

Extracto original

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?

Abrir el original · 19:12 Fuente de la transcripción

La hora de inicio proviene de la transcripción proporcionada. La alineación de la reproducción está pendiente de revisión.