This paper introduces the concept of contextual sequencing as a control structure for autonomous agents (robots). The use of context in the construction and access of a knowledge base is described. The design of a robot using a contextual evaluator is outlined. The benefits, including the ability to readily adapt, to learn, and to pretend are discussed. V4, an implementation of a contextual evaluator, is briefly described. An autonomous creature, implemented as a set of V4 rules, is given and explained as an example of these ideas.