Transparent Multi-Agent AI
summary
Live demo of a working multi‑agent stack that uses Neo4j to record every orchestration step so retrievals, planner outputs, task assignments and tool calls are stored as graph nodes and relationships the demo wires LangGraph agents (an LLM agent and a Neo4j agent) to a Python backend and the needle starter kit UI, shows GraphRAG retrievals tied to specific document chunks, and publishes a GitHub repo so you can reproduce the audit, reuse past plans for repeatability, and inspect per‑run metrics with Neo4j GraphRAG
AI-written summary · about
chapters (12)
- 0:00Introduction to talk
- 1:51Why multi-agent systems
- 3:15Solution framework overview
- 7:05Challenges in multi-agent AI
- 9:33Goals of the framework
- 10:40Current solutions limitations
- 12:04Key features of framework
- 14:12Data model explanation
- 17:03Demo setup and interface
- 18:06Visualizing the audit graph
- 21:56Repeatability with graph data
- 24:10Q&A session
related talks
14mUsing Graphs to Fine-Tune Agents
01h 34mHands-on AI workshop: Graph RAG, Memory & Multimodal Agents
20mEnhancing RAG with Multi-Agent Integration
01h 59mBuilding Agentic and Multi-Agent Systems with LangGraph
32mBuilding Multi-Agent Systems: From Concepts to Collaboration
51mMemory Masterclass: Make Your AI Agents Remember What They Do!
40mAI Agents in Practice
01h 26mThinking in Graphs: The Cognitive Foundations of Agentic AI