Frank Coyle introduces ontologies as explicit representations of entities, properties and relationships, and connects them to the symbolic and neural traditions of AI. He contrasts expert-led domain modelling with bottom-up discovery and describes reusing established vocabularies instead of inventing every concept.
Frank Coyle illustrates how RDFS and OWL relationships can support inference and constraints, then maps those ideas onto an agent tool-use loop. The model proposes a tool invocation, application code executes it and a validator checks whether the result fits the domain before the loop proceeds or asks for help.
Frank Coyle recommends typed input checks alongside domain-level validation, using examples such as duplicate refunds, incorrect recipient roles and unsupported order states. The talk presents an architecture for guardrails, not a demonstrated guarantee that ontologies eliminate all hallucinations or agent failures.
Watch on YouTube
