This session explores how the AI API is used to personalize assignments based on students’ majors and difficulty preferences, enhancing engagement and learning. Using Keller’s ARCS model, the system tailors tasks to boost motivation, relevance, confidence, satisfaction. Attendees will learn about the technology and witness the transformation of traditional assignments.

Instructors teaching multi-major courses frequently encounter the challenge of creating assignments that resonate with students from diverse academic backgrounds. These students often bring unique perspectives, interests, and levels of experience to the classroom, making it difficult to craft a single assignment that engages all students equally. Traditional educational models rely on static, uniform assignments designed for broad application, leaving students either disengaged due to lack of relevance or overwhelmed by misaligned expectations. This dilemma has led many educators to search for more flexible, student-centered approaches. Artificial Intelligence (AI) provides a promising solution by allowing for the dynamic customization of assignments. Through the integration of AI’s Application Programming Interface (API), instructors can now offer students assignments that align with their academic discipline, interests, and preferred challenge level. In this session, we will explore how AI-driven systems can be applied to personalize learning experiences on a large scale. Participants will gain insight into how AI can take student inputs, such as their major and difficulty preference, and generate assignments that are tailored to each individual’s learning path. Research in education consistently shows that personalized learning experiences can dramatically improve student engagement and outcomes. When students feel that an assignment is directly relevant to their academic and professional goals, they are more likely to invest in the task, explore deeper learning opportunities, and perform better overall. In contrast, assignments that feel disconnected from a student’s career trajectory or personal interests can lead to apathy, resulting in poorer academic performance. AI offers an unprecedented opportunity to close this gap by transforming how assignments are developed and delivered. No longer bound by the one-size-fits-all approach, instructors can use AI to create individualized pathways for students, ensuring that each task holds meaning and relevance for the learner. These assignments operate on a couple key inputs: the student’s major and their preferred difficulty level. Different than a prompt, the API processes these inputs to generate a tailored assignment that fits the learner’s academic trajectory. For instance, a biology major and a business major in the same course might receive two different versions of an assignment that focus on concepts relevant to their disciplines. Furthermore, the difficulty level can be adjusted by the student, with the system offering higher levels of challenge for those looking to stretch their skills, while providing foundational tasks for students who prefer a more manageable workload. This customization fosters deeper engagement, as students are more likely to connect with tasks that feel relevant to their individual experiences and future career goals. Importantly, by giving students control over the difficulty level, the system promotes a sense of ownership in their learning process, motivating them to challenge themselves appropriately. Technology and Implementation: The AI-based system for personalized assignments is built on a custom API integration. The process begins when students input their preferences into the system. Based on these inputs, the program generates a unique assignment  tailored to their academic major and selected difficulty. The assignment is not randomly generated but designed to reflect both core course material and specific content relevant to the student’s field of study. A point multiplier can be used and is an innovative feature that allows students to earn higher points for opting into more challenging tasks, promoting a gamified learning environment where taking risks is rewarded. This system ensures that students are fairly evaluated based on the effort and challenge they select. This system is grounded in Keller’s ARCS (Attention, Relevance, Confidence, Satisfaction) model of motivation, a well-established framework for enhancing student motivation through personalized learning strategies. Let’s break down how the dynamic assignments align with each of the ARCS dimensions.  Attention: One of the key benefits of AI-powered personalization is its ability to capture and maintain student attention. In a traditional classroom, uniform assignments may fail to engage all learners, especially in multi-major courses where content might feel less relevant to students in different fields. Personalization through AI, however, captures attention by offering novel, customized tasks that directly relate to the student’s academic interests. The process of choosing difficulty levels and engaging with content that reflects their own field keeps students focused and engaged throughout the assignment process. Relevance: Personalizing assignments based on a student’s major enhances the relevance of the task, which is crucial for motivation. Students see immediate connections between the material they are learning and their future careers, which boosts engagement. For example, an engineering major may receive a math-based assignment with real-world applications in engineering, while a communications major might work on tasks that emphasize data analysis in media. This relevance-driven approach encourages students to invest more effort in their work, as they recognize the direct value of the task to their personal and professional development. Confidence: A core feature of this system is the ability for students to select their own difficulty level, fostering a sense of confidence. By allowing students to determine the level of challenge they are comfortable with, they are empowered to control their learning journey. The point multiplier system ensures that students are rewarded for taking on more difficult tasks, but also that those who prefer less challenging work are still fairly assessed. This approach builds confidence by ensuring students are appropriately challenged and can experience success aligned with their own goals and abilities. Satisfaction: Finally, satisfaction is a critical outcome of personalized assignments. Students derive satisfaction from completing tasks that are both relevant to their interests and appropriately challenging. The adaptive nature of the assignments reinforce their efforts, providing a sense of accomplishment. Moreover, the satisfaction component is further enhanced by the gamified grading system, where difficulty levels and point multipliers offer tangible rewards for effort, driving a cycle of continuous motivation. The integration of AI into assignment design marks a significant evolution in how we approach personalized learning. Through this session, participants will see how AI can not only make assignments more relevant to individual students but also boost motivation and confidence by allowing for flexible difficulty settings. Attendees will leave with practical insights into how this technology can be implemented in their courses, along with an understanding of the pedagogical benefits that come from moving away from static, uniform assignments. Personalized assignments, driven by AI, represent a next frontier in education—offering a dynamic, engaging, and tailored learning experience for every student. The audience will be engaged through witnessing the personalization of assignments in real time, and will interact by providing the presenters inputs to include in the assignment generation / modification.

Dr. Shane Schartz

Associate Professor of MIS, Informatics at Fort Hays State University

Nathan Howard

Assistant Professor at Fort Hays State University