Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

Synthesis

1. 01

   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.

   Supporting evidence 1

   Original excerpt

   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 · 3:45

   Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley · Jul 23, 2026

   Context

   knowledge and, uh, graph technology really represents.

   Read in source context →

   Continue exploring

   ontology design for AI agents →
2. 02

   Neurosymbolic AI as LLM guardrails

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

   Supporting evidence 1

   Original excerpt

   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 · 4:46

   Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley · Jul 23, 2026

   Context

   And so

   Read in source context →

   Continue exploring

   neurosymbolic AI architecture →
3. 03

   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.

   Supporting evidence 1

   Original excerpt

   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 · 16:45

   Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley · Jul 23, 2026

   Read in source context →

   Continue exploring

   agent validation workflow →
4. 04

   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.

   Supporting evidence 1

   Original excerpt

   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 · 19:12

   Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley · Jul 23, 2026

   Read in source context →

   Continue exploring

   ontology-based business logic enforcement →