Runtime verification involves monitoring the system at runtime to check for conformance of the execution trace to user defined safety properties. Typically, run-time verifiers do not assume a system model and hence cannot predict violations until they occur. This limits the practical applicability of runtime verification. Steering is the process of predicting the occurrence of violations and preventing them by controlling system execution. Steerers can achieve this using a limited knowledge of the system model even in situations where it is infeasible to store the entire model. In this paper, we explore a control-theoretic view of steering for discrete event systems. We introduce an architecture for steering and also describe different steering paradigms.