In recent years, the widespread adoption of remote work and online teaching, now encompassing approximately one in five employees, has introduced several operational and health-related challenges. Extended screen exposure often causes digital eye strain, characterized by dryness, visual fatigue, and blurred vision. Additionally, prolonged interaction with digital devices can disrupt circadian rhythms due to blue light exposure, contributing to mental health concerns such as anxiety, sleep disturbances, and cognitive fatigue. The absence of physical oversight in remote settings increases the risk of distractions and unintentional sleep during working hours. To address these concerns, the proposed system employs a real-time drowsiness detection model based on convolutional neural networks (CNN) that concurrently classify the state of the eyes and mouth as open or closed. The system tracks facial expressions and eye dynamics to identify signs of fatigue or drowsiness. By analyzing visual and cognitive behavioral cues, the system provides a comprehensive assessment of user tiredness. When predefined thresholds—such as extended eye closure or repetitive yawning—are exceeded, the system autonomously issues real-time alerts and dispatches email notifications to designated supervisory personnel. This solution supports early intervention and digital wellness through intelligent, non-intrusive monitoring.