An adaptive prognostic tool for bearing was implemented. The on-line learning capability and no historical data requirement are two advantages of the investigated approach. Because the lifetime model parameters are updated on-line using the latest diagnostic information, the remaining useful life (RUL) prediction performance is highly accurate. The approach could be applied in real-time which makes it feasible for use in industry. Actual bearing data were used to demonstrate the efficacy of the approach. The prototype is running in Matlab. We plan to develop a real-time tool in the near future. The detailed demo video is located in the Download section.