ENBLE | Devpost

Inspiration

Many fitness apps rely on generalized workout and nutrition plans that don't account for individual preferences or challenges. As a result, users struggle to balance fitness routines, dietary goals, and busy schedules. Additionally, hiring a personal trainer can be expensive and trainers aren't always available when you need them. The absence of real-time feedback from both apps and trainers makes it hard to adjust plans when life gets hectic or goals change. This lack of personalization and support can lead to a drop in motivation, reducing the app’s effectiveness in helping users achieve their fitness and wellness goals.

What it does

ENBL creates customized workout and meal plans tailored to each user’s specific goals and preferences, ensuring a more personalized approach to fitness. By using public data sources, it provides users with relevant, up-to-date advice that reflects current trends and health insights. Additionally, ENBL features a chatbot that offers real-time support and guidance, making it easier for users to stay on track, make adjustments on the fly, and get the help they need whenever challenges arise. This combination enhances user experience and goal achievement.

How we built it

https://github.com/AVenti-stack/enbl_alpha Front end

After several group meetings, we finalized a strategy focusing on core functionalities. Recognizing the potential for a larger project, we aimed to build an AI-based workout app with monetization opportunities in mind. Guided by design team mood boards, we advanced the project using Flutter and Figma for the front-end.

Backend Integration

For data storage and retrieval, we integrated Quadrant and Pinecone, utilizing LlamaIndex agents for ingestion, indexing, and querying, along with metadata filters to enhance precision. The API provides personalized workout and diet recommendations, while Supabase manages user authentication and data handling. ## Challenges we ran into
Due to time constraints, we couldn't implement all the features we envisioned for the hackathon. However, we prioritized the essential functionalities that aligned with the hackathon's scope and are excited to further refine the app post-hackathon. ## Accomplishments that we're proud of
We’re proud to present a beta version of the app that is 80% functional compared to the full alpha version we had planned. This marks just the beginning of its potential, and we see significant opportunities for future development. ## What we learned
Throughout the hackathon, we learned the importance of prioritizing core features to ensure functionality within a limited time frame, while balancing ambition with practicality. We realized that refining and iterating on a minimum viable product (MVP) can set a strong foundation for future enhancements. Technically, we gained valuable experience integrating tools like Quadrant, Pinecone, and LlamaIndex for efficient data workflows, while Supabase helped us strengthen our user authentication and data handling skills. Additionally, working with AI and public datasets to create personalized solutions taught us how to enhance user engagement. This hackathon highlighted the value of agile development, effective communication, and the ability to adapt to challenges—insights that will guide us as we continue refining and expanding ENBL. ## What's next for ENBLE -To enhance ENBL, future implementations include higher-quality data from fitness experts and influencers, offering users well-rounded guidance. Future features will enable influencers and creators to market their workouts, personalized plans and be a hub to monetize and grow without needing to build an entire app.
work-outs generated based on users availability of equipments. For example if the user doesn’t have a gym membership and limited equipment the workouts generated will be based on the equipment available.
3D image scanning of users to visually track progress.
Implementing image screening that scans barcodes for meal tracking will improve accuracy in diet logging micro and macro nutrients. Enhancing nutrition tracking by expanding data sources ensures better diet management.
Diet plans given out based on users dietary preference, allergy or restrictions. -The app can further adapt workout routines to fit users' daily schedules, if missed, helping maintain consistency. Introducing more detailed feedback and real-time adjustments based on user activity will refine both workout and meal plans, boosting user engagement and success.