FormMaxx

Human Anatomy
Bicep Targeted
Exercise Choices
Video Upload

Inspiration

FormMaxx was inspired by the challenge of improving workout form without access to a personal trainer or just those intimidated by a gym environment. Many people train alone and rely on mirrors or online videos, which often fail to provide precise, personalized feedback. We wanted to explore how AI could help close this gap.

What it does

FormMaxx allows users to select an exercise, upload a video of themselves performing it, and receive AI-generated feedback on their form. The feedback is tailored to the specific exercise and focuses on technique, movement quality, and potential issues.

How we built it

We built a React.js frontend for exercise selection and video uploads, and a Python Flask backend to handle requests and processing. The backend sends the exercise metadata and video to the Gemini API, which analyzes the input and returns structured feedback that is displayed in the frontend.

Challenges we ran into

One major challenge was handling video uploads alongside structured exercise data in a single request. Another challenge was ensuring the AI feedback stayed exercise-specific rather than generic, which required careful prompt design and data structuring.

Accomplishments that we're proud of

We successfully integrated a full-stack workflow that combines video input, exercise context, and AI analysis. We’re proud of building a functional system that delivers meaningful, readable feedback in a clean user experience.

What we learned

We learned how to design and debug a full-stack application involving media uploads, API integration, and asynchronous communication. We also gained experience working with multimodal AI systems and understanding their limitations and strengths.

What's next for FormMaxx

Next, we aim to improve the accuracy and consistency of feedback, expand the exercise library, and explore more advanced form analysis techniques to provide even more actionable insights.