Enhancement of technology-based system support for knowledge workers is an issue of great importance. The "Knowledge work Support System (KwSS)" framework analyzes this issue from a holistic perspective. KwSS proposes a set of design principles for building a comprehensive IT-based support system, which enhances the capability of a human agent for performing a set of complex and interrelated knowledge-works relevant to one or more target task-types within a domain of professional activities. In this paper, we propose a high-level, software-agent based architecture for realizing a KwSS system that incorporates these design principles. Here we focus on developing a number of crucial enabling components of the architecture, including (1) an Activity Theory-based novel modeling technique for knowledgeintensive activities; (2) a graph theoretic formalism for representing these models in a knowledge base in conjunction with relevant entity taxonomies/ontologies; and (3) an algorithm for reasoning, using the knowledge base, about various aspects of possible supports for activities at performance-time.