This study addressed the problem of poor quality control in the built environment due to the limitations of traditional methods, which were often slow, costly, and prone to human error. There was a need to explore how artificial intelligence (AI), particularly machine learning and expert systems, could improve quality control across the construction lifecycle: pre-construction, construction, and post-construction. The study adopted a scientometric and narrative analysis approach. Scientometric methods were used to analyse publication trends, keyword co-occurrences, and country contributions using data from Scopus and Web of Science databases. VOSviewer and Biblioshiny tools were used for data visualisation, while narrative findings explored real-world applications of AI in each construction phase. The findings showed a growing global interest in AI-driven quality control, with increasing publications and citations in recent years. The analysis identified four main clusters: sensor intelligence, intelligent automation, predictive diagnostics, and real-time intelligence. Each cluster contributed uniquely to quality control through data monitoring, decision-making, and predictive maintenance. The study concluded that AI, through machine learning and expert systems, could transform construction quality control by improving efficiency, safety, and performance. However, it also noted the need for further research using real-world case studies and exploring AI adoption in small construction firms.