We study a dynamic contracting problem with multiple agents and limited commitment. A principal seeks to screen efficient agents using one-period contracts, but is tempted to revise contract terms upon knowing an agent’s type. Alterations of contracts are observable and, hence, whenever past promises are broken future information revelation stops. We provide necessary and sufficient conditions under which information revelation can be fostered. For sufficiently patient players, private information is either never revealed or fully revealed in a sequential manner. Optimal contracts provide high-powered incentives upon initial disclosure of an agent’s type, and rewards for information revelation vanish over time.