We describe an architecture for constructing a character-based agent based on speech and graphical interactions. The architecture uses models of emotions and personality encoded as Bayesian networks to 1) diagnose the emotions and personality of the user, and 2) generate appropriate behavior by an automated agent in response to the user’s input. Classes of interaction that are interpreted and/or generated include such things as word choice and syntactic framing of utterances, speech pace, rhythm, and pitch contour, and gesture, expression, and body language. In particular, we describe the structure of the Bayesian networks that form the basis for the interpretation and generation. We discuss the effects of alternative formulations on assessment and inference.