Keeping the trainee on track

Serious games and other training applications have the requirement that they should be suitable for trainees with different skill levels. Current approaches either use human experts or a completely centralized ap-proach for this adaptation. Where agents are increasingly used in serious game implementations as a means to reduce complexity and increase believability, their use for adaptation can lead to situations in which the lack of coordination between the agents makes it practically impossible to follow the intended storyline of the game and select suitable difficulties for the trainee. In this paper we propose an archi-tecture for game design that introduces a monitoring module to check the development of user skills and direct coordinated agent adaptation. Agents propose possible courses of action that are fitting their role and context, and the monitor module uses this information together with its evaluation of user level and storyline progress to determine the most suitable combination of proposals.