A general strategy for treating uncertainties in batch process scheduling was described by Lee and Malone (Int. J. Prod. Res. 2001, in print). The strategy is based on hybridization of the Monte Carlo simulation and simulated annealing techniques. In this paper, the same strategy was used to develop a flexible planning algorithm that handles the open-shop model of batch plant operation and the discrete demand pattern. Using the flexible planning algorithm, we can estimate the maximum capacity of a batch plant and make a capacity plan in the face of uncertainties in product demands and due dates. After the capacity planning, we obtain a flexible plan that maximizes the expected profit and has some free time as a source of future flexibility. An example solved with this flexible planning algorithm shows that it is possible to use only half of the maximum capacity of a batch process because of uncertainty. This means that, in order to reduce the future inventory costs, we should not plan to run a batch process at its maximum production capacity when uncertainty is involved. The lower apparent utilization of the flexible plan will reduce the impact of uncertainties in the future.