In today's commercial world, corporate security and safety are essential elements. Ensuring the safety of personnel, property, and infrastructure becomes critical as businesses expand and function in more complicated and frequently dangerous contexts. Conventional security solutions, such having employees on the scene and manually monitoring video systems, have limits in terms of their scope and efficacy, particularly when it comes to spotting dangers that change quickly, like fire or firearms. Intelligent surveillance systems that make use of cutting-edge technology like computer vision and machine learning are becoming more and more necessary to overcome these constraints. Significant gains in object detection and real-time monitoring capabilities have been made possible by the latest developments in deep learning. One such innovation is the YOLO (You Only Look Once) algorithm, which is renowned for its high-accuracy real-time object detection capabilities. Because of its single-shot detection technique, YOLO can quickly and effectively identify objects in photos or video streams, which makes it a great option for applications that demand quick decision-making and high processing efficiency. The creation of an automated corporate safety system that uses the YOLO algorithm to detect fire and weapons is the idea put forth in this paper. Organizations can enhance security and fire safety measures by automating the identification of weapons, knives, and fire-related threats in corporate environments by incorporating YOLO.