Inspiration
We really want to be able to do a pull up, and we were inspired by the prompt to create an agent that rapidly adapts so we could use it as a personal trainer!
What it does
Our app takes in user data including personal fitness goals, sleep hours, energy, injuries, mood and workout consistency to dynamically create and update a workout plan for the user. The user is also surveyed after each workout so that any changes needed are automatically made to the rest of that week's workouts.
How we built it
We created the front end in flutter, then used Python FastAPI to handle the requests sent to GeminiAPI, which generated personalised workouts in a JSON form. We also used FireBase to create a multi-table database to store user and workout data.
Challenges we ran into
We were both new to flutter, so we had a slow learning process at the start and coding in dart. We also had never collaborated on github together, so we had to learn new commands and a workflow that was efficient for us. We got a lot better towards the end of the hackathon!!!
Accomplishments that we're proud of
Creating a working app after many challenges and a lot of sleep deprivation :( We are also proud of how professional but fun the app looks as we haven't done much front-end work before!
What we learned
How to work as a team with an efficient workflow, how to program using Dart for the first time and a lot of github and vscode commands!
What's next for FitFlow
Creating an online community of users with a leaderboard based on workouts completed, utilising the existing database. We also want to have apple health data as an input to help customise workouts better, maybe based on sleep hours and steps count.
Log in or sign up for Devpost to join the conversation.