An agentic ai for dietary counseling and personalized weight management
Using a unique data set of 90k+ minutes of discussions between dietitians and patients, we are constructing an AI agent that will be able to provide clinically validated counseling to patients. Our team has expertise in AI development, LLM fine tuning with patient level data, behavioral interventions, and chronic disease management. Our model will not only use this data but will also be built as RAG to incorporate the latest literatures on GLP Agonists to assist in counseling. We are currently pursuing federal funding to validate our approach using a clinical trial but are open to other funding and development approaches. Our team is highly skilled and coordinated and has had over 5 years experience working together on similar projects.
Our team has also developed methods using Reinforcement Learning (RL) to personalize weight management incentives and exercise goals to study participants. These methods have been validated, and we are currently testing one of them using a NIH clinical trial. We are also open to developing these further.
About University of Wisconsin, Madison
The University of Wisconsin–Madison is the state’s flagship public research university, a comprehensive institution with a large research enterprise and broad disciplinary breadth. Industry engages through shared instrumentation, pilot‑scale testbeds, and co-located core facilities that support prototyping and scale-up. An affiliated research and technology park hosts startups and corporate R&D, while integration with a major hospital system enables clinical translation; a statewide extension network connects campus advances to companies and communities across Wisconsin. Research is sustained by competitive federal funding from agencies such as NIH, NSF, DOE, USDA, and DoD, alongside state and industry partnerships. Dedicated commercialization support—through an affiliated foundation and campus offices—provides IP management, licensing, startup mentoring, and flexible, industry-friendly agreements.
delivered to your inbox.