Automating Supply Chain Disruption Monitoring via an Agentic AI Approach

Modern supply chains are increasingly vulnerable to disruptions. This paper introduces a minimally supervised agentic AI framework that autonomously monitors, analyzes, and responds to disruptions across extended supply networks. The architecture uses seven specialized LLM-powered agents and deterministic tools to detect disruption signals, map them to multi-tier networks, evaluate exposure, and recommend mitigations. The system achieves high accuracy and significantly reduces response time compared to traditional methods. A real-world case study demonstrates its operational applicability for building resilient, proactive, and autonomous supply chains.