​Automatic Ontologies: Build the Context Graph for Trustworthy AI Agents, Yann Bilien, Rippletide

In this part of the talk, the speaker explains that building context graphs was actually a huge pain point at first. Their team spent 18 months in R&D, working with some bright minds and testing real enterprise deployments, to figure out how to automate graph creation—especially using ontologies. They share real production examples, like a testing agent that checks code every time someone commits to a repo, larger data-heavy graphs, and even a credit decision system for a car manufacturer. What makes these context graphs different is that they combine three things: structured knowledge (entities and relationships), built-in processes so decisions aren’t left entirely to language models (avoiding issues like hallucinations), and guardrails that enforce clear, deterministic rules. Even though a lot of people are interested in using context graphs, far fewer have actually deployed them in production—mainly because setting them up is tough, especially when integrating multiple data sources and managing large, complex graphs.

You will learn:
• Why AI agents fail without structured context — and how context graphs fix this
• What makes a production-ready context graph: knowledge, processes, and guardrails
• How graph-based ontologies eliminate the need for RAG pipelines at scale
• How to evaluate context graph quality by measuring agent performance
• How to manage graph updates without breaking consistency

Real-world examples include:
• A coding test agent that runs automatically on every repo commit
• A credit decision system for a car manufacturer
• A data-heavy enterprise knowledge graph

If you have considered building a context graph but have not reached production — this talk is for you.

Learn more about Context Graphs: https://neo4j.com/blog/context-graphs/
Rippletide docs: https://docs.rippletide.com/

—

0:00 Introduction — Yann Bilien, Rippletide
1:30 Production Context Graph Examples
3:30 Three Components of a Context Graph (Knowledge, Processes, Guardrails)
5:00 The Three Challenges of Building Context Graphs
7:00 Graph-Based Ontologies: The Alternative to RAG Pipelines
10:00 Evaluating Context Graph Quality via Agent Performance
12:00 Managing Graph Updates and Consistency
13:30 Key Benefits and How to Get Started