In practice, software developers and test teams generate functional tests with the help of user interface (UI) automation tools. Despite these tools, especially for large-scale applications, developers and test teams must (1) produce test steps from given test scenarios, (2) execute the test steps, and (3) evaluate if the test has passed or failed by observing the application behavior. FARLEAD-Android is a fully automated test generation engine which accomplishes these tasks for the developers and test teams. In this preliminary study, we evaluate FARLEAD-Android on a large-scale banking application. In our experiment, FARLEAD-Android reaches 54.55% of the activities, verifies the correct execution of six different functions, and reveals issues in three different functions during verification in approximately 24 minutes. Our evaluation shows that FARLEAD-Android must have an experience replay feature, investigate fragments along with activities, and use a human-readable test scenario format.