Work-related musculoskeletal disorders (WMSDs) remain a major concern in occupational health, requiring reliable and objective postural assessment to support effective prevention strategies. Although observational methods such as the Rapid Upper Limb Assessment (RULA) are widely adopted, their manual application is subjective, time-consuming, and difficult to scale in dynamic work environments. Thus, this study develops a computer vision–based automated solution for ergonomic risk assessment, capable of identifying and classifying work-related upper-body postures using the RULA method. Guided by the Design Science Research Methodology, the artifact was implemented in Python using OpenCV and MediaPipe Pose to detect upper-body landmarks, compute joint angles, and automatically assign RULA scores for the upper arm, lower arm, neck, and trunk. The solution was demonstrated and evaluated in educational and office-like environments, analysing 3,316 video frames from standing and seated tasks. The results indicate consistent detection of postural deviations and generation of time-resolved RULA scores capturing variations in trunk flexion, neck inclination, and upper-limb elevation. Agreement analysis using Fleiss’ kappa showed perfect concordance and predominantly moderate to fair agreement across several demonstrations, confirming that the solution provides ergonomic classifications consistent with expert assessments while capturing variability in challenging postural conditions. Additionally, the solution generates spreadsheets and annotated videos, enabling longitudinal analysis of postural behaviour across tasks, thereby reducing subjectivity and maintaining alignment with established RULA criteria. By integrating ergonomic principles with computational automation, this study offers a replicable, low-cost, non-intrusive approach to risk assessment, supporting decision-making and preventing work-related health disorders, and promoting sustainable work environments.