We present a workbench to build, evaluate and iteratively develop user interfaces using augmented reality, eye tracking, and visual programming. To test our system, we have developed an attentive user interface (AUI) for automotive environments, which coordinates its activities based on the context and visual attention of the user. Development of AUI requires interdisciplinary teams like psychologists, human-factor engineers, designers and computer scientists to work together. The main problem of interdisciplinary communication is a lack of common language and different notion of the system. We have developed a workbench, which facilitates the communication between the team members and enhances the comprehension of the system by visualizing users' attention and system reactions.

Mobile augmented reality applications promise substantial savings in time and costs for product designers, in particular, for large products requiring scale models and expensive clay mockups (e.g., cars). Such applications are novel and introduce interesting challenges when attempting to describe them to potential users and stakeholders. For example, it is difficult, a priori, to assess the nonfunctional requirements of such applications and anticipate the usability issues that the product designers are likely to raise. In this paper, we describe our efforts to develop a proof-of-concept AR system for car designers. Over the course of a year, we developed two prototypes, one within a university context, the other at a car manufacturer. The lessons learned from both efforts illustrate the technical and human challenges encountered when closely collaborating with the end user in the design of a novel application.