It is well recognized that all cumulative information should be used, whenever appropriate, to aid in decision making in the approval process of medical products. Bayesian methods provide a natural framework and convenient tools to incorporate cumulative information from historical studies to improve precision, and to derive statistical inference via the informative posterior distribution. However, the use of Bayesian methods to incorporate historical data in clinical trial design and analyses is still limited likely due to i) incorrect perception that it will not be accepted by regulatory agencies, and ii) limited understanding about various Bayesian methods (which ones to use, and how?). Unfortunately there is not going to be a one-size-fit-all Bayesian method. The use of particular Bayesian models and specification of prior distributions need to be assessed on a case-by-case basis. Moreover, the acceptance of particular Bayesian designs may also depend on the nature of the disease and existing treatment options. For instance, a slightly inflated Type I error rate might be acceptable to regulatory agencies in certain settings but not in others.