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:
- a second refund on the same order,
- a payout going to the support desk instead of the buyer,
- an order status like “probably shipped.”
Proposed fix
His answer is a neurosymbolic stack:
- probabilistic reasoning stays inside the model,
- logic and constraints live outside it,
- and tool calls are validated before the agent can act.
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.
More from coding & agent
- Bindu Reddy tests an AI brain with long-term memory on his own work — bindureddy · 2026-07-23
- GPT-5.6 reads the code while Fable 5 keeps probing MCP calls until it works — Angaisb_ · 2026-07-23
- Open-source WeChat Channels download Skill lets users save videos by URL — vista8 · 2026-07-23
- Fleet engineering turns vibe coding into parallel AI coding sessions — victor_explore · 2026-07-23
- Open repo packages 21 chapters of agentic design patterns with code notebooks — tom_doerr · 2026-07-23
- Keel Code launches with a loop of frontier models that keeps coding agents going until the goal is done — Scobleizer · 2026-07-23