Automating Radio Communication Training: A Protocol-Aware Chatbot Using Context Engineering for Human-centric Industrial Operations

In human-centric industries such as transportation and heavy manufacturing, strict adherence to safety-critical radio communication (RC) protocols is essential for operational efficiency and safety. Traditional training methods rely on human instructors, who may introduce inconsistencies or biases. While chatbots present a scalable alternative, conventional Retrieval-Augmented Generation (RAG) systems often fail to enforce protocol compliance reliably. Hence, a protocol-aware training chatbot is proposed to bridge this gap, leveraging context engineering and few-shot learning with Large Language Models (LLMs) to deliver industry-specific and protocol-compliant responses. Validated through a transportation case study, this chatbot system demonstrates robust consistency in RC protocol enforcement across 18 scenarios of varying complexity. An integrated scoring mechanism evaluates trainee performance and provides corrective feedback, enhancing learning outcomes. By providing practical and human-like experiences in RC training, this system can be adapted across industries to reduce miscommunication risks.