One of the principle causes for deviations between predicted and simulated performance of buildings relates to the stochastic nature of their occupants: their presence, activities whilst present, activity- dependent behaviours and the consequent implications for their perceived comfort. A growing research community is active in the development and validation of stochastic models addressing these issues; and considerable progress has been made. But one key outstanding challenge relates to the integration of these emerging prototype models with building simulation in a coherent and generalizable way; meaning that emerging models can be integrated with a range of building simulation software. One promising approach is to integrate stochastic occupancy models within a multi agent simulation (MAS) platform, which communicates directly with building simulation software. My research uses this approach.