The concept of joint action is at the core of numerous diverse research topics, including philosophical explorations of social action, studies of human dialogue, human-computer interaction, computer-supported collaborative work, multiagent systems, distributed artificial intelligence, distributed simulation, and contract law. It is therefore remarkable that so central a concept has received so little detailed analysis, in comparison with studies of individuals. However, in recent years, the study of joint action has begun to undergo more intense scrutiny, primarily from philosophers and researchers (...) in artificial intelligence. These two disciplines often address similar topics but with different motivations, methodologies, tools, and criteria for success. Although this paper is inspired by philosophical work, it is squarely motivated by the concerns of building intelligent systems that are capable of collaborative behavior, either with a user, or with other such systems. Still, we hope that the paper sheds light on philosophical issues, and treats the subject of joint action at a sufficiently precise level to be illuminating of problems that any philosophical account needs to confront. (shrink)