Beyond RAG: Building the AI Corporate Brain with Knowledge Graphs and Virtue Ethics
summary
Argues that combining knowledge graph + Graph ML with vector search/LLM RAG builds an "AI Corporate Brain" that maps customers, products, processes and personnel in Neo4j (Aura/Deployment Center links provided) and shifts from document retrieval to explicit reasoning; claims this architecture cuts hallucinations by grounding answers in graph relationships, embeds ethical guardrails via the H.E.V.I.D.S. layers (Harmony, Ethics, Veracity, Integrity, Discernment, Safeguards), and surfaces actionable insights rather than isolated documents.
AI-written summary · about
chapters (9)
- 0:00Introduction corporate AI dilemma
- 2:35Trust deficit in AI systems
- 5:25From data to knowledge hierarchy
- 7:31Why RAG falls short
- 8:52Knowledge graphs as corporate brain
- 11:37Adding virtue ethics layer
- 13:20HEVID model explained
- 16:30Knowledge graphs and ethics synergy
- 17:54Path to trustworthy AI
related talks
36mAgentic GraphRAG: AI’s Logical Edge
42mMaking OSS AI Real with Knowledge Graphs
01h 26mThinking in Graphs: The Cognitive Foundations of Agentic AI
27mLies, Damn Lies, and AIs
27mWhen Vectors Aren’t Enough: Unlocking AI’s Hidden Connections with Graphs
30mAgentic RAG with Knowledge Graphs Explained
53mPractical GraphRAG - Making LLMs smarter with Knowledge Graphs
01h 40mKnowledge Graphs & GraphRAG: Techniques for Building Effective GenAI Applications