Timely, relevant, and accurate intelligence analysis is critical to national security, but it is astonishingly complex. This paper provides an intuitive overview of Cogent, a cognitive assistant that facilitates a synergistic integration of analyst's imaginative reasoning with agent's critical reasoning to draw defensible and persuasive conclusions from masses of evidence, in a world that is changing all the time. It presents Cogent's design goals characterizing a new generation of structured analytical tools, introduces the evidence-based analysis concepts on which it is grounded, illustrates a sample session with its current version, and summarizes the cognitive assistance provided to its user.

Evidence-based reasoning is at the core of many problem solving and decision making tasks in a wide variety of domains. This paper introduces a computational theory of evidence-based reasoning, the architecture of a learning agent shell which incorporates general knowledge for evidence-based reasoning, a methodology that uses the shell to rapidly develop cognitive assistants in a specific domain, and a sample cognitive assistant for intelligence analysis.