In today's rapidly evolving business landscape, leaders face an overwhelming amount of information spread across multiple formats and sources. From procurement documents to operational data and technical documentation, extracting relevant insights can be time-consuming and inefficient. The sheer volume of disorganised and inconsistent data further complicates decision-making, leading to delays, missed opportunities, and potential financial risks. As businesses increasingly rely on data-driven strategies [1], the need for more effective ways to process and analyse information has never been greater.

Retrieval-Augmented Generation (RAG) technology offers a powerful solution by combining information retrieval with generative AI. Unlike traditional search methods, which simply return matching documents, RAG systems retrieve relevant data and generate contextualised responses, providing users with precise and meaningful insights [2]. This approach significantly enhances efficiency, allowing users to quickly access critical information without manually sifting through extensive records. By integrating AI-powered retrieval and generation, RAG applications can improve decision-making across various business domains.