Prior studies identified effective, but mainly non-digital, homework aids. This research involved 18 middle school students in a lo-fi prototyping study to integrate traditional homework support tools with intelligent tutoring systems (ITS), leveraging rich log data for personalized learning. Feature investigations in standardized diaries, goal setting, homework graphing, and reminders revealed a preference for goal-setting, informing a refined prototype exploring students' attitudes towards self-set versus system-generated goals. Results indicate students prefer system-recommended goals, express goals by problem count and time, and value goal difficulty feedback to foster autonomy. Providing data-driven feedback and fading system-set goals in ITS could improve self-regulation during homework practices and equity.