The benefits of Service Oriented Architectures (SOA) for business, such as reduced costs and development time, are well recognised, however one of the most challenging steps in using SOA is defining the correct composition of services for a particular business process. Quickly recognised as a task where computer automation could help, various approaches have been proposed, including the use of AI techniques for planning service compositions. However, these techniques can perform poorly due to the search space explosion caused by dealing with the vast number of available services that must be composed. In this paper we present an approach to composing Web services, using software agents to enact plans of actions which achieve organisational goals, where each action specifies what should be achieved as opposed to which service to use. When enacting an action, agents use a matchmaking process to determine services that can be used to achieve the desired effects, intelligently handling any errors that may occur. The action plans are based on an organisation model in which organisational goals are refined into scenes, landmarks, and objectives, allowing the set of actions available to the plan synthesis mechanism to be tailored to the goal being targeted at that specific time, further reducing the planning search space.