This research presents a groundbreaking approach to diagnosing waterproofing issues in buildings, leveraging advanced Artificial Intelligence (AI) techniques to significantly enhance accuracy and efficiency. The framework focuses on developing a robust AI model using the k-nearest neighbors (KNN) classifier to deliver precise diagnostic results. By employing real-world data for validation and performance assessment, the study demonstrates the potential of the AI model to outperform traditional diagnostic methods. This innovative approach not only increases the accuracy of identifying waterproofing problems but also provides stakeholders in the construction and building maintenance sectors with valuable insights. As a result, they can make more informed decisions to ensure the structural integrity and longevity of buildings. This research highlights the transformative impact of AI in the construction industry, offering a more reliable and efficient solution to waterproofing diagnostics, ultimately leading to better-maintained structures and reduced long-term costs. The proposed AI-driven framework represents a significant advancement in building maintenance technology, promising substantial benefits for the industry.