UC Berkeley talk says agent systems need ontologies to catch errors prompts miss

AI Engineer · youtube · 2026-07-23

Frank Coyle argues agent systems need ontologies as guardrails

In this UC Berkeley talk, Frank Coyle says many agent failures come from a missing layer outside the model: a formal ontology that acts as logical guardrails.

Problem examples

He points to failure modes such as:

Proposed fix

His answer is a neurosymbolic stack:

He suggests using standards such as RDFS and OWL, plus practical checks like Pydantic and ontology validation around a Claude tool-use loop.

Main takeaway

English instructions are too fragile for many real workflows. Typed entities, relationships, and constraints can catch errors that prompt engineering cannot.

Original post →

More from coding & agent

coding & agent channel →