Next-Gen Travel Agents: Merging AI Agentic and Neo4j for Personalized Experiences
summary
A prototype Berlin museum itinerary generator uses LangGraph to orchestrate multiple LLM agents, Next.js for UI, Neo4j for graph storage and Neo4j routing, and Wikidata as the source. Agents split responsibilities — museum expert, itinerary maker, map generator — and collaboratively produce a one‑day plan, but non‑deterministic behavior causes long runs (one example takes 24 iterations), token cost, and brittle name matching in the graph; it works functionally but needs tighter control and real‑time feedback to be reliable.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 2:05Museum Planner
- 3:08Agentic AI
- 7:43Application Architecture
- 11:53Example
- 20:58Whats next
related talks
29mTransparent Multi-Agent AI
29mBuilding Modular AI Agents with LangGraph, MCP, and
57mCrafting Intelligent Agents with Context Engineering
29mAgentic AI with Knowledge Graphs on the JVM: A Music Graph in Practice
53mHands-on with AI agents: From scratch to LangGraph
01h 30mHow to build AI Agents: A step by step guide to creating AI agents
29mAgentic GraphRAG: Multi-Agent Knowledge Graph Construction for Research Teams
21mUI in The Age of AI