You are viewing content from a past/completed conference.
Explicit Semantics for AI Applications: Ontologies in Practice
Abstract
Modern AI applications struggle not because of a lack of models, but because meaning is implicit, fragmented, and brittle. In this talk, we’ll explore how making semantics explicit (using ontologies and knowledge graphs) changes how we design, build, and operate AI systems. Drawing on real work from the GoingMeta.live podcast series, we’ll look at how ontologies move from theory to practice: grounding LLMs, improving reliability, enabling reasoning, and creating shared understanding across teams and systems. Expect concrete patterns, lessons learned, and examples you can apply to production AI today.
Speaker
Jesús Barrasa
Field CTO for AI @Neo4j
Dr. Jesús Barrasa is the Field CTO for AI at Neo4j, where he works with organisations combining the power of LLMs with Knowledge Graphs. He co-authored "Building Knowledge Graphs" (O'Reilly 2023) and is cohost of the Going Meta live webcast (https://goingmeta.live/). Jesús holds a Ph.D. in Artificial Intelligence/Knowledge Representation and is an active thought leader in the KG and AI space.
Read more
Find
Jesús Barrasa
at:
From the same track
Session
agentic coding
The Right 300 Tokens Beat 100k Noisy Ones: The Architecture of Context Engineering
Wednesday Mar 18 / 10:35AM GMT
Your agent has 100k tokens of context. It still forgets what you told it two messages ago.
Patrick Debois
AI Product Engineer @Tessl, Co-Author of the "DevOps Handbook", Content Curator at AI Native Developer Community
Baruch Sadogursky
DevRel Team and Context Engineering Management @Tessl AI, Co-Author of #LiquidSoftware and #DevOps Tools for #Java Developers, Java Champion, Microsoft MVP
The Right 300 Tokens Beat 100k Noisy Ones: The Architecture of Context Engineering
Session
data platform engineering
Building an AI Ready Global Scale Data Platform
Wednesday Mar 18 / 01:35PM GMT
As organizations move from single-cloud setups to hybrid and multi-cloud strategies, they are under pressure to build data platforms that are both globally available and AI-ready.
George Peter Hantzaras
Engineering Director, Core Platforms @MongoDB, Open Source Ambassador, Published Author
Building an AI Ready Global Scale Data Platform
Session
Your Agent Sandbox Doesn't Know My Authz Model: A Standard-Shaped Hole
Wednesday Mar 18 / 02:45PM GMT
Sandboxes are the first line of defence for agentic systems: restrict the bash commands, filter the URLs, lock down the filesystem. But sandboxes operate on the syntax of requests, not the semantics of your authorization model.
Paul Carleton
Member of Technical Staff @Anthropic, Core Maintainer of MCP
Your Agent Sandbox Doesn't Know My Authz Model: A Standard-Shaped Hole
Session
AI/ML
Beyond Benchmarks: How Evaluations Ensure Safety at Scale in LLM Applications
Wednesday Mar 18 / 11:45AM GMT
As LLM systems move from prototypes to production, the gap between benchmark performance and real-world reliability becomes impossible to ignore. Models that score well on benchmarks can still fail unpredictably when facing the complexity, ambiguity, and edge cases of real users.
Clara Matos
Director of Applied AI @Sword Health, Focused on Building and Scaling Machine Learning Systems
Beyond Benchmarks: How Evaluations Ensure Safety at Scale in LLM Applications