What is this project?
This project challenges students to design a system that transforms complex Standard Operating Procedures (SOPs) into functional AI agents within the enterprise system at JPMorgan Chase. These agents will automate enterprise tasks by converting human workflows into machine-executable instructions. The outcome will help the organization dramatically improve efficiency and reduce manual process overhead. All student team members will become JPMC 2026 Summer Interns, based in Chicago, IL.
Eligibility: Due to JPMorgan Chase internship HR requirements, only undergraduate students who are US Citizens or permanent residents with an expected graduation between December 2026 and June 2027 are eligible for this team.
Important Requirement: This project includes and requires participation in a paid JPMorgan Chase summer 2026 internship, located in Chicago. Students who cannot fulfill this requirement are not eligible for the project.
By September 30th (Note this is prior to the main MDP application deadline):
To be considered for this team, in addition to the MDP application, you must complete The JPMorgan Chase internship application [linked here], selecting Chicago as your preferred location.
If you have questions about this, please contact MDP at engin-MDP@umich.edu
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 functional AI agents that will convert human workflows into machine-executable instructions.
- Identify key user interactions within SOPs that involve system data retrieval
- Define and document APIs, including OpenAPI specifications, for those interactions
- Build mock tools with IDA-authenticated clients to simulate API behavior using dummy data
- Translate SOPs into executable Runbooks by embedding tool calls and prompts
- Develop and validate an agent using an agentic framework to execute the Runbook logic with test scenarios
- Tech Stack: See more information on the Student Skills tab
Stretch Goal Opportunities Include:
- Use LLM-assisted techniques to suggest or even generate tool stubs from SOP text automatically, accelerating the API-to-tool build process
- Extend the system to support multiple cooperating agents (e.g., one for data collection, one for verification) to tackle more complex workflows
Why does it matter?
Manual execution of SOPs in enterprise environments is time-consuming, error-prone, and hard to scale. This project tackles a pressing industry challenge: turning dense procedural documents into intelligent automation. The solution improves operational efficiency, supports compliance, and lays the groundwork for scalable AI-driven enterprise systems – goals aligned with modern digital transformation efforts.
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.
Intermediate NLP (1-2 students)
Specific Skills: Intermediate experience in NLP
Must have completed EECS 281 or equivalent prior to enrollment
Likely Majors: CS, DATA, ROB, SI
Web System Design (1-2 Students)
Specific Skills: Web System creation and an interest expanding your experience in NLP
Must have completed EECS 281 or equivalent prior to enrollment. Ideally will be co-enrolled in AI/NLP course
REST APIs
Likely Majors: CS, BBA
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.
- Interest in and general knowledge of Commercial Banking
- Successful team-based project experience
- Excellent interpersonal skills and the willingness to work hard
- Project Management utilizing Agile/Scrum
- Tech Stack
- Programming Language: Python
- Libraries and Frameworks:
- Pydantic: data validation and settings management
- Langchain: creating runnable chains
- Azure CLI: interacting with Azure services
- Azure Identity: authentication
- Logging: logging messages
- Cloud Services:
- Azure OpenAI: Interacting with Azure OpenAI services
- Tools:
- Threading: concurrent execution
- Datetime: date manipulations
- Data Formats:
- JSON: data serialization and deserialization
- Familiarity with software architecture design
- Experience with Git/GitHub workflows
- Prior exposure to language models or prompt engineering
- List all NLP courses and projects you have worked on in your application materials
- Experience in business process analysis
- Practical Experience with any/most of our tech stack
- Chatbots, Java, Python, NLU, NoSQL database, Spring Boot, Rest APIs, HTTPS based applications. Be sure to address this on your experience and interest form
- Note – it is unlikely that any student would be fully competent in the entire tech stack before the project. Significant individual training effort is expected and required
- Practical experience implementing predictive analytics in a complex data environment
Recommended Coursework
- EECS 485: Web Systems
- EECS 492: Introduction to Artificial Intelligence
- EECS 487: Intro to NLP
- EECS 595: NLP (with Transformers & LLMs)
- SIADS 655: Applied NLPs
Sponsor Mentor
Uday Pant
Uday is a Senior Director for Data and AI/ML Operations at JPMorgan Chase. He is an IT Leader with deep expertise in building large scale and customizable software solutions. Uday has worked at JPMorgan Chase for 10 years, and has also worked at Amazon Web Services and Cognizant Technology Solutions.
Executive Mentor
Todd Ippen
Executive Director, Global Technology
Todd Ippen is a Senior Director of Engineering in CIB Global Banking Technology – Wholesale Client Servicing at J.P. Morgan in Chicago, Illinois. Mr. Ippen has been with the firm for over 25 years portraying many roles from application development to multi-year program management involving architecture required to support numerous lines of businesses and products. Mr. Ippen is presently the head of Global Workflow Solutions where he is responsible for simplifying how we do business for our clients, partners and Wholesale Lending Service employees, by delivering a modern and robust connected eco-system with global workflow and enhanced automation and AI/ML/LLM capabilities in support of Loan Booking/Originations, Document Prep & Review, Loan Servicing including Covenant Management, Collateral, Insurance & Pledging. Outside of his day to day activities, Mr. Ippen is the JP Morgan Captain for University of Michigan recruiting and is a member of the Chicago Tech Center Work Recruiting Workstream and was responsible for bringing and expanding AWS DeepRacer to the firm globally. In his free time, Mr. Ippen enjoys spending time with his wife and two children travelling, boating, skiing, attending various sporting activities and supporting his daughter’s love for dance.
Faculty Mentor
Shai Revzen
Associate Professor, Electrical and Computer Engineering
Shai’s research interests include the study of bio-inspired robotics and new methods and mechanisms for control. He has also been involved with the scientific study of animal and human locomotion based on nonlinear dynamical systems, and application to design of legged robotic vehicles and other devices.
BProject Meetings
During the winter 2026 semester, the JPMC team will meet on North Campus on TBD.
Work Location
This project will take place on campus in Ann Arbor, with remote access to JPMorgan systems during Winter 26/Fall 26. All project team members are required to participate in the JPMorgan summer 2026 internship program, based in their Chicago, IL office.
Course Substitutions: CE MDE, ChE Elective, CS Capstone/MDE, CoE Honors, ROB Flex Tech
Citizenship Requirements: Students selected for this team must have the right work in the U.S.A indefinitely, without sponsorship. All student team members are required to participate in JPMC 2026 summer internship program in Chicago, IL.
IP/NDA: Students will sign an IP and NDA agreement that is unique to JPMC.
Summer Project Activities:
Summer 2026 Internships will be located in Chicago, Illinois. They are guaranteed and required for all students who match to this project team. Every student who accepts an offer to join this project team must also participate in the summer internship with JP Morgan. The internship runs from early June to early August.
- All project students must participate in the JPMorgan summer internship program, and will be based in Chicago, Illinois
- All students must
- be undergraduate students with an expected graduation between December 2026 and June 2027.
- Have the right to work in the United States indefinitely without sponsorship
- Have cumulative University of Michigan GPA > 3.0
- Pass a background and drug test
- To be considered for this team, in addition to the MDP application, you must complete The JPMorgan Chase internship application [linked here], selecting Chicago as your preferred location.
If you have questions about this, please contact MDP at engin-MDP@umich.edu - MDP project offer letters will include required dates, compensation, and other conditions of the internship. Students will have 10 days to accept or reject their combined MDP/JPMC offer, which will be sent approximately October 20.