Agent-Oriented conceptual modelling notations are highly effective in representing requirements from an intentional stance and answering questions such as what goals exist, how key actors depend on each other and what alternatives must be considered. In this paper, we suggest an approach to executing i* models by translating these into set of interacting agents implemented in the CASO language. In addition, we suggest a hybrid modelling, or co-evolution, approach in which i* models and CASO agent programs are concurrently maintained and updated, while retaining some modicum of loose consistency between the two. This allows us to benefit from the complementary representational capabilities of the two frameworks.