Abstract: Timely feedback is essential for students to learn and improve their performance. However, it is hard for computing instructors to provide real-time feedback for every student, particularly during homework or online classes. While researchers have put tremendous effort into developing algorithms to generate automated feedback, little work has evaluated how this feedback actually helps in practice, or what specific design choices make it more or less effective. In my dissertation, I am designing and evaluating different features of automated feedback, specifically next-step hints. Inspired by educational theories and effective human feedback, this work has the goal of discovering automated feedback design choices that can improve students' performance and learning.