A significant portion of the existing infrastructure, including bridges and buildings, is reaching the end of its operational lifespan due to aging, heightened operational demands, and challenging weather conditions. Considering these circumstances, it becomes imperative to conduct periodic inspections of bridges. In the realm of Structural Health Monitoring (SHM), conventional inspection methods face challenges of high costs, time inefficiencies, and safety risks for inspectors. This paper introduces an innovative approach that leverages Augmented Reality (AR) and Artificial Intelligence (AI) to redefine the landscape of structural inspections. The proposed system eliminates the need for heavy and expensive equipment, presenting a safer and more cost-effective alternative. With the integration of AR technology, inspectors can remotely assess bridge conditions without physical presence in hazardous or inaccessible areas. The system employs a machine learning model, capable of detecting and classifying multiple types of damage, including cracks and spalling. The simplicity and efficiency of the approach not only streamlines the inspection process but also substantially reduces associated costs. Furthermore, the system goes beyond detection by quantifying the length, area, and perimeter of identified damage, offering a comprehensive understanding of damage severity. This combination of AR and AI not only revolutionizes bridge inspections but also represents a paradigm shift toward a safer, more cost-effective, and efficient monitoring methodology. The potential impact on industry practices and inspector safety underscores the significance of the approach in the field of SHM. This paper presents results collected from a field test conducted on a full-scale bridge in Ontario. These results conclude that the system successfully detects cracks and spalling and quantifies their severity.