Passionfruit - Skills Gap Analyzer

Pursue your passion and bear the fruits of your success!

Comment

Inspiration

Passionfruit was inspired by the challenges job seekers face in today's competitive market, especially when it comes to interview preparation. We noticed that while there are many resources for learning technical skills, there's a gap in tools that help candidates practice and improve their interview presence, communication, and confidence. We wanted to create an AI-powered platform that provides personalized, real-time feedback to help users put their best foot forward in interviews.

What it does

Passionfruit is an AI-powered interview coach that helps users practice and improve their interview skills through:

Real-time Mock Interviews: Uses TensorFlow.js and MediaPipe FaceMesh for in-browser face detection to track eye contact, smile detection, head pose, and speaking activity.

Personalized Feedback: Provides real-time metrics and post-interview analytics to help users understand their performance.

Resume Integration: Extracts skills from uploaded resumes to generate tailored interview questions.

Performance Analytics: Tracks progress over time with detailed session reports and visual feedback.

How we built it

Passionfruit is built with a modern web stack: Frontend: Next.js 15 with TypeScript and Tailwind CSS AI/ML: TensorFlow.js and MediaPipe FaceMesh for real-time face tracking State Management: Zustand for global state Styling: Custom animations with Framer Motion and Tailwind CSS Data Visualization: Recharts for performance metrics Authentication: Firebase Auth Database: Firestore for user data and interview history

Challenges we ran into

  1. Real-time Processing: Implementing smooth, real-time face tracking in the browser without significant performance issues was challenging.
  2. Cross-browser Compatibility: Ensuring consistent behavior across different browsers, especially with WebRTC and TensorFlow.js.
  3. Accurate Metrics: Fine-tuning the algorithms for eye contact detection and other behavioral metrics to provide meaningful feedback.
  4. Responsive Design: Creating an intuitive UI that works seamlessly across different devices and screen sizes.
  5. Time Constraint: There was only 8 hour for the entire hackathon, not including mandatory breaks, so it was stressful.

Accomplishments that we're proud of

  1. Building a comprehensive interview preparation tool that helps users improve both technical and soft skills.
  2. Creating a responsive UI with smooth animations and intuitive feedback mechanisms.
  3. Developing a system that provides actionable feedback to help users become more confident and effective interviewees.

What we learned

  1. The importance of performance optimization when working with real-time computer vision in the browser.
  2. Best practices for creating accessible and user-friendly interfaces for complex features.
  3. Working on very specific deliverables under small time constraints.

What's next for Passionfruit

Expanded Question Bank: Adding more industry-specific questions and scenarios. AI-Powered Mock Interviews: Implementing more sophisticated AI interviewers that can ask follow-up questions based on user responses. Multi-round Interview Simulations: Creating end-to-end interview experiences that mimic real-world interview processes. Peer Practice: Adding features for users to practice with peers and receive feedback from the community. Mobile App: Developing native mobile applications for on-the-go interview practice. Integration with Job Platforms: Partnering with job boards and career platforms to provide seamless interview preparation for specific job postings.

Built With

Share this project:

Updates