There is a great deal we do not know about the safety of pharmaceutical agents, especially regarding their safe use in the workplace. Economic and scientific imperatives can lead to a new drug's approval and marketing even though testing is limited; therefore, much of the knowledge about drug toxicities must be developed in the postapproval period, through pharmacoepidemiologic methods. The system of epidemiologic intelligence depends on spontaneous, voluntary reports of adverse drug reactions and, as applied to the work force, it is fraught with problems of ascertainment, accountability, and application. Structured epidemiologic studies of these issues have been difficult to perform because of high costs, long time frames, and methodologic problems and biases. Nevertheless, large automated data bases, with the right input, hold great promise for making it easier to accumulate and analyze the data necessary for monitoring drug safety in the workplace.