Improving Access to Building Licensing Information in Australia: Design and Development of a Graph-Based Retrieval-Augmented Generation (RAG) Artificial Intelligence (AI) System

Digital technologies have been widely adopted to improve efficiency, transparency, and decision making in the construction industry. However, regulatory processes such as building license and registration applications remain complex, fragmented, and difficult for applicants to navigate, particularly for early career practitioners and small businesses. This study presents the design and development of a graph-based retrieval-augmented generation (RAG) artificial intelligence (AI) system that assists users in applying for building licenses and registrations in Australia. By integrating eight regulatory burden frameworks, this study identified ten categories of licensing-related burden. A three-layer system architecture was subsequently proposed for the Australian construction licensing context, and a prototype is implemented using the New South Wales (NSW) regulatory framework. The system provides context-aware responses, step-by-step guidance, and tailored information based on user queries, thereby reducing regulatory burden for individuals, companies, and industry bodies. Prototype evaluation against general-purpose AI tools indicates improved information accessibility and reduced application-related friction in representative licensing scenarios. This study sheds light on AI-enabled regulatory support systems and demonstrates how graph-based RAG could improve accessibility and usability of construction related licensing processes. The findings have implications for policymakers, regulators, and researchers seeking to leverage AI to support digital transformation in the construction industry.