Business Intelligence (BI) capitalized on datamining and analytics techniques for discovering trends and reacting to events with quick decisions. We argued that a new breed of data-mining, namely stream-mining where continuous data streams arrive into the system and get mined very quickly, stimulates the design of a new real-time BI architecture. In the past, stream-mining (especially in algorithmic level) and digital information system architectures have been studied separately. We attempted in this paper to present a unified view on the real-time BI system architecture powered by stream-mining. Some typical applications in which our architecture can support are described.