Smart systems that apply complex reasoning and machine learning to make decisions and carry out actions are rapidly becoming part of everyday user interaction, yet so far most of these systems are like black boxes and not at all transparent. It has been shown that intelligibility can help users interact with a system more effectively, promote positive attitudes towards the system, increase their trust in the system's decisions and actions, and to gain a sense of controllability. My research has focused on providing explanations – textual and graphical – of the behaviour of intelligent systems to make these systems more intelligible. In this talk I will provide a brief overview of what we know about how to design for intelligibility so that users understand how an intelligent system works.
7