Ontologies Are So Back: Why AI Agents Are Reviving the Semantic Web
- ID
- 9048
- Status
- summarized
- Published
- 30 Jul 2026, 7:17 PM
- Fetched
- 30 Jul 2026, 7:27 PM
- Provider
- Latent Space
- Category
- developer-ai
- Original URL
- https://www.latent.space/p/ontologies-agentic-systems
- Source URL
- https://www.latent.space/feed
Summary
- Score
- 7.5
- Created
- 31 Jul 2026, 4:35 PM
- Tags
- Audience
- developersai_ml_learnersai_agent_users
What happened
At the AI Engineer World's Fair 2026, UC Berkeley professor Frank Coyle argued that agentic systems need ontologies as deterministic guardrails around probabilistic LLMs, calling the convergence 'neurosymbolic AI.' He noted that established web ontologies like Schema.org, FOAF, and Dublin Core are already in LLM training data, so developers can prompt for them directly rather than inventing new ones. Neo4j CEO Emil Eifrem outlined three ontology types for running agents at scale: business-facing ontologies, technical metadata ontologies, and execution traces from agent runtime signals.
Why it matters
If you're building AI agents, you can stop designing knowledge schemas from scratch and instead prompt LLMs to use existing ontologies like Schema.org or Dublin Core that are already baked into their training data — this gives you free deterministic structure to validate agent reasoning. Teams evaluating graph databases for agent infrastructure should look at how Neo4j's three-layer ontology model (business concepts, technical metadata, execution traces) maps to their own stack.
Discussion angle
Which existing ontologies (Schema.org, FOAF, Dublin Core) could you immediately prompt an LLM agent to use for your domain, and does combining them with a graph database like Neo4j actually reduce hallucination enough to justify the added complexity over plain RAG?