Navigating the maze of regulatory documents is a daunting task for anyone. Imagine sifting through hundreds of pages of dense legal text, searching for inconsistencies and potential conflicts. This is the challenge researchers tackled by exploring the potential of Large Language Models (LLMs), specifically GPT-4, to automate this complex process. The Hackitt Review, sparked by the Grenfell Tower tragedy, highlighted the critical need for clearer and more consistent building regulations. Existing methods struggle with the sheer volume and complexity of these documents, making compliance a significant hurdle. Researchers investigated whether AI could offer a solution. They designed an experiment where GPT-4 was tasked with analyzing regulatory texts, focusing on detecting inconsistencies and contradictions. These inconsistencies were deliberately inserted into the text, allowing researchers to assess GPT-4's accuracy. The results were promising. GPT-4 demonstrated an ability to identify these discrepancies, offering a potential pathway towards automated regulatory compliance. While the initial results are encouraging, more research is needed. Future work will involve larger datasets and fine-tuning the model for specific domains like fire safety and structural integrity. The ultimate goal is to develop an AI tool that not only identifies inconsistencies but also suggests solutions, making compliance more efficient and ultimately, contributing to a safer built environment.