Fittracker

Inspiration

We were inspired to create FitTrack to bridge the gap between raw fitness data and actionable insights. Many users track their health, but often lack personalized guidance to truly achieve their goals. Our aim was to build an intelligent platform that not only logs data but also empowers users with tailored recommendations and expert advice.

What it does

FitTrack is an all-in-one application for logging workouts, tracking nutrition, and monitoring physical progress. It provides intuitive analytics and AI-powered recommendations to help users understand their habits and optimize their health journey. Additionally, an interactive AI assistant offers personalized advice on various health and fitness topics.

How we built it

The frontend was developed using React and TypeScript, styled with Tailwind CSS, and bundled with Vite for a fast development experience. Supabase served as our comprehensive backend, handling the PostgreSQL database, user authentication, and serverless Edge Functions. These functions facilitate secure communication with the Google Gemini 2.0 Flash AI for intelligent features.

Challenges we ran into

Whenever there were issues, bolt.new suggested lines of code to fix but sometimes these were not accurate. We had to run code locally and find the correct line.

One challenge was to find out how everything worked together, reverting changes is not as seamless as we would like in a collaborative environment.

Integrating AI is easy to do but you need to provide bolt.new specific details of which LLM you're going to use like version, tier and possibly provide an example of the LLM. We learned about edge functions and these help secure our interactions with LLMs.

Accomplishments that we're proud of

We are particularly proud of seamlessly integrating advanced AI capabilities to provide personalized health suggestions and an interactive chat experience. Building a robust system for comprehensive data tracking across workouts, nutrition, and progress in one platform was a key achievement. We also successfully developed an intuitive analytics dashboard that transforms complex data into clear, actionable insights.

What we learned

We learned how easy is to build applications with AI with little knowledge of the technologies used, in my case, React.

What's next for Fittracker

For the future, we envision advanced goal setting with AI-assisted adjustments and predictive progress tracking. Integrating with popular wearable devices will allow for automatic data import, further enriching user insights. We also plan to introduce AI-powered meal planning and expand community features for enhanced user interaction.

Built With

• eslint
• gemini
• postgresql
• react
• supabase
• typescript