Building the Perfect Supply Chain Chatbot
summary
Claims a Neo4j-powered chatbot can answer compliance and incident questions in seconds instead of days by traversing a graph that links products, ingredients, lab results, suppliers, shipments and corrective-action records. Demonstrates a simple feedback-to-workflow loop that captures negative responses and creates triage work items, and an incremental deployment pattern that starts with one domain (R&D or testing) then expands the graph. Shows how the bot locates a bad batch, which customers received it and which alternate suppliers meet specs. graph-first integration lab-to-shelf tracing
AI-written summary · about
chapters (8)
- 0:00Introduction and speakers
- 2:47Current challenges in chatbots
- 7:04Workflow and feedback mechanisms
- 10:42R&D use case for chatbots
- 16:48Product recall and incident management
- 21:51Testing environment integration
- 26:26Graph architecture and scalability
- 29:23Q&A and closing remarks
related talks
29mKnowledge graph based chatbots
13mExploring AI-Powered Chatbots and Their Transformative Role
16mGraphRAG for Supply Chain Resilience: Building an AI Supplier Discovery Engine
01h 36mTutorial: From Planni...
10mMastering LLM Chatbot Testing: Metrics, Methods and Mistakes to Avoid
30mThe GraphRAG System That Asks Back: Intelligent Probing with Better Contextual Answers
16mGraph-Powered Compliance: Building Intelligent Regulatory Mapping with AI and Neo4j
20mPower Amazon Bedrock applications with Neo4j knowledge graph