← All popular talks

Popular talk #12

Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley

Frank Coyle21:18

Now playing

Teaching Philosophy

0:00

Join the discussionComment on this moment0:00

Synced transcript

Follow the talk

Teaching Philosophy
Two Lineages
Neurosymbolic AI
Building Ontologies
Reuse Taxonomies
RDFS & OWL
Agents & Loops
Claude Loop
Pydantic Guard
OWL Errors
Conclusion

Community discussion

What did you agree with—or push back on?

Specific reactions make these talks more useful. Draft here, add the moment you’re discussing, then choose the direct-post pilot or the YouTube handoff.

Automated overview

What this talk covers

Frank Coyle argues that most agent failures, from brittle tools to fragile handoffs, stem from missing formal ontologies as logical guardrails. He proposes neurosymbolic AI: probabilistic reasoning inside, logic outside. An ontology is typed entities, relationships, and constraints expressed with RDFS and OWL, letting you specify a payment status must be one of three values, that a customer and support rep are different, or that an order can only be refunded once. Wrapping a Claude tool use loop with a validator—Pydantic at the door for types, ontology at the ledger for results—catches errors like a second refund on the same order, a payout sent to the support desk instead of the buyer, or an order status of 'probably shipped' that English instructions cannot reliably prevent.

This overview is derived from the transcript and has not been independently fact-checked by AI Engineer.

Chapters

  1. 0:00Teaching Philosophy
  2. 2:17Two Lineages
  3. 4:23Neurosymbolic AI
  4. 5:24Ontology Basics
  5. 6:24Building Ontologies
  6. 8:04Reuse Taxonomies
  7. 9:19RDFS & OWL
  8. 12:09Agents & Loops
  9. 14:23Claude Loop
  10. 17:43Pydantic Guard
  11. 18:59OWL Errors
  12. 20:29Conclusion