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.