Nemo

Inspiration

The inspiration for Nemo came from recognizing the challenges underserved communities face in accessing healthcare and essential services. Stories like Jeremy's—where individuals lack insurance, transportation, and basic resources—motivated us to create a solution that not only connects people to healthcare providers but also to vital community services such as food pantries and shelters. Our goal was to leverage technology to make a real difference in people’s lives, ensuring that no one is left behind due to barriers in the system.

What it does

Nemo is an AI-powered mobile app designed to help underserved communities access healthcare and essential services. It connects users to the right insurance plans, books medical appointments, and locates community services such as food pantries, shelters, and mental health resources—all tailored to their specific needs.

How we built it

We built Nemo using a combination of Generative AI, Natural Language Processing (NLP), and Retrieval-Augmented Generation (RAG) to ensure personalized recommendations. We started by conducting exploratory data analysis to understand the specific needs of underserved populations. From there, we integrated data from local databases and built the AI engine to interpret user queries and provide real-time, customized suggestions based on user location, health conditions, and needs.

Challenges we ran into

One of the major challenges was ensuring that Nemo provides accurate, real-time recommendations from a variety of sources, while maintaining a user-friendly experience. We also had to tackle the issue of limited access to technology in underserved areas, ensuring that our solution could run smoothly on low-end mobile devices. Another challenge was aligning our AI model to make precise insurance and community service recommendations that fit the user's specific circumstances.

Accomplishments that we're proud of

We’re proud of creating a platform that goes beyond just healthcare access. Nemo offers a holistic approach by connecting users with community-based services, truly addressing the multifaceted challenges they face.

What we learned

We learned the importance of understanding the real, lived experiences of the people we’re trying to serve. By focusing on their needs, we were able to design a more effective and empathetic solution. Additionally, working with AI models in such a sensitive space taught us the value of continuous refinement and feedback to improve recommendation accuracy.

Built With

• api
• c++
• ec2)
• firebase-(for-real-time-data-sync)-**apis**:-google-maps-api-(for-service-location-tracking)
• genai
• generation
• healthcare.gov-api-(for-insurance-data)
• javascript-**frameworks**:-flask-(for-backend)
• llm
• local-community-service-apis-**ai/ml-technologies**:-generative-ai-(openai-models)
• natural-language-processing-(spacy)
• openai-api-(for-generative-ai)
• python
• rag
• react-native-(for-mobile-frontend)-**platforms**:-android
• retrieval-augmented
• s3