In this paper, we discuss the architectural aspects of a Smart Personal Assistant (SPA) system that enables users to access a range of applications from a range of devices using multi-modal natural language dialogue. Each back-end application is a personal assistant specializing in one speci ?c task such as e-mail or calendar management, and typically each has its own user model, enabling it to adapt to the user?s changing preferences. The PDA interface to the SPA must present the system as a single uni?ed set of backend applications, enabling the user to conduct a dialogue in which it is easy to switch between these applications. Furthermore, the system?s interaction with the user must be tailored to their current device. The SPA is implemented using an agent platform and includes a special BDI coordinator agent with plans both for coordinating the actions of the individual assistants and for encoding the system?s dialogue model. The plan-based dialogue model is at a high level of abstraction, enabling the domain-independent plans in the dialogue model to be reused in different SPA systems.