We are excited to announce a groundbreaking service that leverages the power of generative AI to transform how LSA departments manage and disseminate information. The LSA Department GenAI Assistant project, powered by the U-M Maizey GPT platform developed by U-M Information and Technology Services (ITS), aims to equip departments with a toolkit to create AI-driven online assistants tailored to their specific needs. By implementing this technology, LSA units can streamline responses to inquiries, enhance user engagement, and reduce the workload for department staff.
Project Overview
U-M Maizey GPT, developed and supported by ITS, is a generative AI platform available to all active U-M faculty, staff, and students on the Ann Arbor, Flint, and Dearborn campuses and Michigan Medicine. This tool allows U-M faculty, staff, and students to enrich their GenAI experience based on a custom dataset that they provide. This service empowers users to extract valuable insights, discover patterns, and gain deeper knowledge from the available datasets.
The LSA Department GenAI Assistant project was conceived to help departments implement this technology across multiple datasets. This will address a common challenge faced by many departments: the substantial time and effort spent responding to inquiries from prospective students, family members, donors, alumni, and other stakeholders. Often, the information sought is readily available on department websites, yet the task of directing individuals to the right resources remains labor-intensive. By leveraging Maizey to develop a department-specific AI assistant, LSA departments and units can provide instant, accurate responses to users, thereby freeing up staff to focus on more complex and value-added tasks.
The project began in June of 2024 with an ambitious timeline that culminated in the launch of the toolkit last month. Key milestones included holding a kickoff meeting, developing a prototype AI assistant, crafting customer service and support best practices, and creating and disseminating the toolkit to all LSA departments.
Benefits of the GenAI Assistant
The primary advantage of the GenAI Assistant is its ability to provide instant, 24/7 responses to inquiries based on publicly available department web content. This ensures that users have access to accurate information at any time, without the need to wait for office hours or staff availability. Departments will benefit from reduced email and phone inquiries, allowing staff to focus on strategic initiatives and personalized interactions that require human touch.
Toolkit and Implementation Process
The GenAI Assistant Toolkit is a comprehensive guide designed to help departments create and integrate their own AI assistants using the U-M Maizey GPT platform. It includes detailed instructions on configuring the AI, connecting data sources, and best practices for ensuring accurate and helpful responses. Key steps in the process include:
Creating MCommunity groups to manage administrative and user access.
Configuring AI settings by adjusting various parameters like “prompts,” “chunks” and “temperatures” to fine-tune the AI's performance.
Integrating Google Drive folders, public website URLs, and other data sources that AI will use to generate responses.
Conducting extensive testing to ensure AI provides accurate and relevant answers.
Launching the AI Assistant by making it publicly available and promoting it to the intended audience.
Active learning, particularly through small group work, has been shown to enhance student engagement, retention, and satisfaction. When students collaborate in small groups, they retain more information and report higher levels of learning than those in traditional instructional settings (Davis 1993, Barkley, 2005). However, the success of group activities depends on thoughtful design that encourages collaboration and accountability. Let’s explore how to ensure successful collaboration and group work.
Structure effective groups
Think about how you will organize students into groups. Take into consideration the size of your class, the type of assignment, and the amount of work/time involved. Typically smaller groups of 2-4 students work best. Larger groups may decrease the opportunity for participation. Intentionally assign groups by schedule availability, work preferences, skill level, and/or background knowledge.
Peerceptiv, an LSA supported tool that supports peer review and group assignments, can help with the group formation process. Peerceptiv allows you to create optimized student groups using student survey responses, which are based on a customizable set of questions and criteria. Students can enter their schedule information, rank topic preferences, and respond to multiple choice questions, all of which will be used by the Peerceptiv Group Formation algorithm to form student groups.
Set expectations and establish group guidelines
It is important to explain how groups will operate and how students will be graded within the group. Determine if students will receive a group grade, individual grade, or a combination of both. Creating and sharing a rubric with grading criteria helps students establish group expectations and guidelines within their group.
Taking time in class to discuss how to effectively work as a group is essential for successful group work. Some topics to discuss may include determining roles and responsibilities, developing a group communication plan, how to keep track of each group member’s progress, and how to resolve disagreements or issues that may arise. Consider having groups work together as the first task to create a shared guidelines document which contains agreed-on expectations of how all group members will contribute and behave, and is a proactive plan of how to work as a group and mitigate conflict (Cao & Renda, 2020).
Provide feedback and measure collaboration
Scaffolding the group project into smaller chunks with multiple deadlines benefits both you and the students. It helps everyone stay on track and allows you to check-in on groups and provide feedback. Students are able to reflect on the group progress, touch-base with group members, and utilize your feedback as they continue working.
Using peer evaluations can encourage collaboration and accountability. This can be done informally as a group discussion to reflect on the work done by themselves and by the group, it could be done as a survey students complete during and/or after the project, or it could be assigned as an individual reflection essay. In addition to asking students how each group member contributed to the overall project, consider asking students to reflect on how well they collaborated with others, such as:
- I asked my group members for help when …
- I accepted help from my group members when …
- I offered to help my group members when …
Peerceptiv also allows for students to anonymously evaluate their team members participation and contributions to their group using the Team Member Evaluation tool.
If you’d like to speak with an instructional consultant about group work, you can request a consultation here. LTC is always happy to help!
References/Additional Resources:
Barkley, E., Cross, P., & Major, C. (2005). Collaborative Learning Techniques. San Francisco: Jossey-Bass.
Cao, A. & Renda, M. (2020). Classroom Strategies for Group Management. University of Michigan Center for Research on Teaching and Learning in Engineering.
Davis, B. (1993). Tools for teaching. San Francisco: Jossey-Bass.
