What is this project?
Faculty and staff at Michigan Engineering lose valuable time to repetitive administrative tasks, like updating calendars, managing file clutter, and notifying supervisors of leave. This project will build a secure, modular web application deployed on AWS that automates and streamlines these routine processes, using smart workflows and AI-enhanced recommendations. The student-built Digital Clutter Buster will save time, clean up digital storage, and lay the groundwork for scalable automation tools across the College.
What am I going to do?
MDP projects push you to integrate interdisciplinary engineering knowledge, and develop strategic problem-solving skills. On this project, students will develop an AI tool that will streamline digital information management for Michigan Engineering faculty and staff.
- Design and build a modular web interface using React or a similar framework
- Integrate Google OAuth and Google Workspace APIs for Calendar, Drive, and People data
- Implement backend logic using Flask, FastAPI, or AWS Lambda (Python preferred)
- Develop the Out of Office Manager to automate meeting cancellations, calendar entries, and supervisor notifications
- Create the Google File Cleaner dashboard with metadata-based sorting and AI-assisted cleanup suggestions
- Deploy and test the platform securely on AWS using U-M account controls
- Write user-facing documentation for helper modules and future extensibility
A successful project will deliver a fully functioning web application with the following features:
- Secure U-M Google Single Sign-On with role- and permission-aware access
- A completed and deployed Out of Office Manager helper
- A completed and deployed Google File Cleaner helper
- Modular backend architecture that supports the addition of future helper tools
- Deployment on AWS with proper logging, error handling, and user profile management
- Documentation for helper modules and deployment pipeline
Stretch Goal Opportunities Include:
- Implement a third helper tool, such as a cross-platform Data Finder, based on AI Explorers recommendations
- Add a summarization feature using LLMs for email or file review tasks
- Enable user-configurable helper workflows for even more automation flexibility
Why does it matter?
Administrative burdens are a significant hidden cost in higher education. By automating common workflows, this toolkit enables faculty and staff to focus on teaching, research, and service, instead of repetitive digital chores. The project showcases how AI and automation can deliver tangible productivity gains, especially in environments with complex tools like Google Workspace and MCommunity. This is an investment in the infrastructure of academic work.
Below are the skills needed for this project. Students with the following relevant skills and interests, regardless of major, are encouraged to apply! This is a team-based multidisciplinary project. Students on the team are not expected to have experience in all areas, but should be willing to learn and will be asked to perform a breadth of tasks throughout the two-semester project.
Web Application Dev (2 students)
Specific Skills: React.js, UI/UX design, form handling
Students must have completed EECS 281 or equivalent. SI students must have REACT experience
Likely Majors: CS, SI-HCI
Business Logic and Modeling- AI/ML (2 Students)
Specific Skills: Workflow definition, prompt design, policy rule modeling
Unsupervised Learning, Heuristic Rule-Based AI, NLP, NER, Semantic Search / Embeddings (eg SBERT)
Likely Majors: DATA, CS, ECE
Backend/API Integration (2 Students)
Specific Skills: REST, AWS Infrastructure, Google APIs (Drive, Calendar),
Students must have completed EECS 281 or equivalent
Likely Majors: CS, CE
Database and System Security (1 Students)
Specific Skills: Google SSO, access control, plugin architecture
Students must have completed EECS 281 or equivalent
Likely Majors: CS, CE
Additional Desired Skills/Knowledge/Experience
Strong candidates will have familiarity or experience with some of the following items, and a positive attitude to learn what is necessary, as the project gets underway.
- Experience working as on a previous project team
- Full stack development experience
- Familiarity with Google Workspace tools and admin permissions
- Experience using AWS services such as Amplify, EC2, or DynamoDB
- Understanding of OAuth 2.0 security protocols
- Knowledge/Experience in working with any of the following tools/techniques/models: Sentence-BERT models, cosine similarity, OpenAI GPT, BART, T5, OpenAI API, HuggingFace Transformers, custom prompt logic, spaCy, or HuggingFace
Recommended Coursework
Include completed relevant courses (term, institution, course number/title, and grade). If you’ve completed any of the following courses, we recommend mentioning them in your application materials:
- DATASCI 415: Data Mining & Statistical Learning
- EECS 505: Computational Data Science & Machine Learning
- EECS 281: Data Structures and Algorithms
- EECS 485: Web Systems
- EECS 484: Database Management Systems
- EECS 453: Principles of Machine Learning
- EECS 553: Machine Learning (ECE)
Sponsor Mentor
Nicole Heffernan
Director of Web Services at CAEN
Nikki, a U-M alumnus, has spent the last 25 years in IT starting as a web developer and now leads a team of developers, business analysts, and project managers that work on a variety of web and other IT projects for the college. Nikki enjoys working with others to find creative solutions to problems.
Tom Knox
With over two decades in his role as Director of Web Services at Michigan Engineering, Tom is an experienced web application developer who loves working in higher education. He is Pythonist at heart, who also works well in Java, and various front-end web frameworks & technologies. Deep down, Tom is fanatical about automation, devops, and being proud of what you put out into the world.
Faculty Mentor
Aaron Elam
Serving as the Lead Generative AI Specialist for the College of Engineering, Aaron is an insightful and results-driven Information Technology leader with a demonstrated record of success in rapidly changing higher education environments. While project managing numerous transitions, integrations, and conversions to optimize online learning and program development, he has continually strategized for current and future needs by remaining abreast of emerging innovations to maximize performance. As an engaging interpersonal communicator, Aaron is adept at building positive relationships across all levels while leading and collaborating with multi-functional teams, students, faculty, and staff. Employing a customer-centric approach to service and support, he strives to continually improve customer/student engagement while positioning them for success.
Project Meetings
During the winter 2026 semester, the project team will meet on North Campus on TBD.
Work Location
Most of the work will take place on campus in Ann Arbor.
Course Substitutions: ChE Elective, CS Capstone/MDE, CoE Honors
Citizenship Requirements: All students may participate in this project.
International Students: CPT declaration is NOT required because the sponsor is internal to the University.
IP/NDA: Students will sign standard University of Michigan IP/NDA documents.
Summer Project Activities: No summer activity will take place on the project.