This paper presents a novel methodology for automated multi-tier supply chain mapping, leveraging Retrieval-Augmented Generation (RAG) and network science techniques. We developed an RAG-based approach that extracts supplier-customer relationships from unstructured public data sources, including SEC 10-K filings and earnings calls. The extracted entities are structured into a directed supply chain graph and analysed using network science metrics such as centrality, modularity, and path length. The case study focuses on three of the largest contract manufacturers in the electronics industry: Hon Hai Precision Industry (Foxconn), Flex Ltd., and Jabil Inc. Our findings demonstrate that Generative AI (GAI), specifically LLMs enhanced with RAG, can construct scalable and comprehensive supply chain graphs. The proof of concept is successful, as evidenced by the construction of a directed supply chain graph encompassing 4,644 nodes and 8,341 edges, covering three of the largest contract manufacturers in the electronics industry.
PRACTITIONER SUMMARY
Modern supply chains are globally dispersed and increasingly vulnerable to disruption, yet most organisations still lack visibility beyond their Tier 1 suppliers. This paper introduces a practical, automated method that uses GAI with Retrieval-Augmented Generation (RAG) to map multi-tier supply chains using publicly available information such as SEC 10-K filings and earnings call transcripts. The approach extracts supplier–customer relationships from unstructured text and converts them into a structured network view of a firm’s upstream and downstream partners. For practitioners, this method offers a scalable alternative to traditional manual mapping, which is often slow, incomplete, and expensive. Using three major electronics manufacturers—Foxconn, Flex, and Jabil—as examples, the study demonstrates that AI can rapidly uncover thousands of supply chain links that would be difficult to compile by hand. Network-science metrics further help identify concentration risks and bottlenecks. The methodology provides three practical benefits: (1) improved visibility into Tier 2 suppliers where critical vulnerabilities often exist; (2) enhanced resilience planning by highlighting highly connected or high-risk nodes; and (3) stronger decision support for compliance checks and stress-testing.