Going Meta S03E08 – The Graph Behind the Graph: Tracing Ontology Design Decisions

Season 03 Episode 8 of Going Meta – a Series on Semantics, Knowledge Graphs and All Things AI
Topic: The Graph Behind the Graph: Tracing Ontology Design Decisions
Build an ontology with an agentic skill, capture every modeling choice as a context graph, and query the reasoning behind the model.

Jesús Barrasa: https://twitter.com/BarrasaDV
Repository: https://github.com/jbarrasa/goingmeta
Knowledge Graph Book: https://bit.ly/3LaqE6b
Previous Episodes: https://neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/

Neo4j Agent Memory: https://neo4j.com/labs/agent-memory/
Context Graphs: https://neo4j.com/labs/agent-memory/explanation/memory-types/
MCP: https://neo4j.com/developer/genai-ecosystem/model-context-protocol-mcp/
Evaluating Quality of Ontologies: https://www.youtube.com/live/16oBgsWPX1o

0:00 Introduction
5:27 The Value of Semantic & Knowledge Layers
9:03 The Problem: Lost Ontology Design Decisions
11:56 Recap: Agent Skills & Agent Memory Package
16:33 Setup: Claude Desktop with Agent Memory MCP
20:44 Running the Ontology Builder with Reasoning Trace
24:00 Watching the Trace Build Live in Neo4j
28:04 Ontology Quality Evaluation Step
30:55 Querying the Reasoning Trace for Past Decisions
36:13 Wrap-up

#graphdatabase #neo4j #graphrag #knowledgegraphs #ontology #data