Everyone's Talking Context Graphs. Here's What One Really Is
About this episode
Daniel Davis co-created TrustGraph, the open-source context backend for AI agents trending on GitHub. He asked every major AI service a simple hockey question, every single one got it wrong. Then he traced why: Wikipedia editors you can hire to plant fake information, a DoD decision where 9 out of 10 experts were dead wrong, and compounding misinformation where AI cites AI until nobody can find t
Key moments
- 0:00 Can AI get simple facts right?
- 1:35 What is a context graph — and who's faking it?
- 9:29 Is a context graph just a rebranded knowledge graph?
- 14:26 Why 2025 was the year AI POCs failed
- 18:07 When 9 out of 10 experts were wrong
- 24:34 How Wikipedia gets weaponized to poison AI
- 29:23 Is my RAG + Neo4j approach actually correct?
- 36:07 What are "statements about statements"?
- 41:03 What happens when your data changes over time?
- 49:12 Why TrustGraph dropped Neo4j entirely
- 52:42 His doomsday prediction for AI
- 55:23 The one book every leader should read
- 1:00:07 outro