We present a model of sense-making that greatly facilitates the collaboration between an intelligent analyst and a knowledge-based agent. It is a general model grounded in the science of evidence and the scientific method of hypothesis generation and testing, where sense-making hypotheses that explain an observation are generated, relevant evidence is then discovered, and the hypotheses are tested based on the discovered evidence. We illustrate how the model enables an analyst to directly instruct the agent to understand situations involving the possible production of weapons (e.g., chemical warfare agents) and how the agent becomes increasingly more competent in understanding other situations from that domain (e.g., possible production of centrifuge-enriched uranium or of stealth fighter aircraft).

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.

Mixed-initiative assistants are agents that interact seamlessly with humans to extend their problem-solving capabilities or provide new capabilities. Developing such agents requires the synergistic integration of many areas of AI, including knowledge representation, problem solving and planning, knowledge acquisition and learning, multiagent systems, discourse theory, and human-computer interaction. This paper introduces seven aspects of mixed-initiative reasoning (task, control, awareness, communication, personalization, architecture, and evaluation) and discusses them in the context of several state-of-the-art mixed-initiative assistants. The goal is to provide a framework for understanding and comparing existing mixed-initiative assistants and for developing general design principles and methods.