Semantic Web technologies are part of multi-agent engineering, especially regarding knowledge base support. Recent advances in the field of logic for the semantic web enable a new range of applications. Among them, programming agents based on semantic rules is a promising field. In this paper we present an semantic agent model that allows SWRL programming of agents. Our approach based on the extended finite state machine concept results in a three layers architecture. We detail the architecture, the syntax of the rules , the agent interpreter cycle and present a prototype validating the concept.