Systems for tracking faces using computer vision have recently become practical for human-computer interface applications. We are developing prototype systems for face-responsive interaction, exploring three different interface paradigms: direct manipulation, gazemediated agent dialog, and perceptually-driven remote presence. We consider the characteristics of these types of interactions, and assess the performance of our system on each application. We have found that face pose tracking is a potentially accurate means of cursor control and selection, is seen by users as a natural way to guide agent dialog interaction, and can be used to create perceptually-driven presence artefacts which convey real-time awareness of a remote space.