A Bayesian blackboard is just a conventional, knowledge-based blackboard system in which knowledge sources modify Bayesian networks on the blackboard. As an architecture for intelligence analysis and data fusion this has many advantages: The blackboard is a shared workspace or "corporate memory" for collaborating analysts; analyses can be developed over long periods of time with information that arrives in dribs and drabs; the computers contribution to analysis can range from data-driven statistical algorithms up to domain-specific, knowledge-based inference; and perhaps most important, the control of intelligence-gathering in the world and inference on the blackboard can be rational, that is, grounded in probability and utility theory. Our Bayesian blackboard architecture, called AIID, serves both as a prototype system for intelligence analysis and as a laboratory for testing mathematical models of the economics of intelligence analysis.

Because uncertain reasoning is often intractable, it is hard to reason with a large amount of knowledge.

Defeat mechanisms are strategies for achieving victory over an opponent. Although defeat mechanisms often rely on influencing the opponent psychologically and emotionally, most simulations of warfare do not model these "soft" factors, they model only victory by attrition. To create more accurate, adaptable, and believable systems, we must be able to model a variety of defeat mechanisms. We propose a model where parameters and attributes that affect emotional and physical fatigue are combined to produce an overall measure of fatigue called effective fatigue. Effective fatigue, along with an agent's state, is combined by a defeat model to produce probabilities of surrender. We create warfare scenarios involving catastrophe and surprise, and then examine the model's behavior under these scenarios. We conclude with a discussion of how the model is related to our own Capture the Flag wargaming system.