Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

AI Engineer · Veröffentlicht am 23. Juli 2026 · Dauer 21:18

Frank Coyle explains ontologies as shared conceptualizations for agents, proposes neurosymbolic guardrails for probabilistic LLMs, and discusses validating tool outputs and catching business logic errors with ontologies. Lies 4 Standpunkte mit Belegen und Links zu den Originalquellen.

Frank Coyle

Kernaussagen lesen Auf YouTube ansehen

Auf einen Blick

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.
Unterstützendes Moment lesen · 3:45
Neurosymbolic AI as LLM guardrails
Frank Coyle argues that neurosymbolic AI can help keep probabilistic LLMs on guardrails.
Unterstützendes Moment lesen · 4:46
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.
Unterstützendes Moment lesen · 16:45
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.
Unterstützendes Moment lesen · 19:12

Schlüsselmomente4

Kurze, zitierte Textstellen mit Kontext zur Überprüfung. Das vollständige Gespräch bleibt beim Herausgeber.

3:45

ontology design for AI agents

Ontologies as formal shared conceptualizations

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.

Frank Coyle·23. Juli 2026

Kontext

knowledge and, uh, graph technology really represents.

4:46

neurosymbolic AI architecture

Neurosymbolic AI as LLM guardrails

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.

Frank Coyle·23. Juli 2026

Kontext

And so

16:45

agent validation workflow

Ontology-driven validation in agent loops

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.

Frank Coyle·23. Juli 2026

19:12

ontology-based business logic enforcement

Ontologies for catching domain-specific errors

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?

Frank Coyle·23. Juli 2026

Quelle & Methodik

Diese Standpunkte sind mit ihren Originalquellen verknüpft. Paraphrasen sind gekennzeichnet und keine wörtlichen Zitate.

Transkript oder Quellenmaterial öffnen Ein Problem melden