Momentum

Landing page
SignIn page
Signup Page
user overview
problem solving
AI Resume Analysis
AI Mock Interviews
Job available
Recruiter Portal
Job posting
Job listing
Applicants

Inspiration

Hiring today is inefficient, fragmented, and unclear for both sides of the table. Recruiters are overwhelmed with large volumes of resumes that often fail to reflect real-world skills, while candidates prepare blindly without understanding how they are evaluated or what truly differentiates a strong candidate from an average one.

This disconnect inspired us to build Momentum — a platform designed to help recruiters confidently select the best candidate, while simultaneously helping users become that best candidate. The name Momentum comes from physics, where momentum is defined as:

$$ \text{Momentum} = mass \times velocity $$

Once an object gains sufficient momentum, it becomes difficult to stop. Careers work the same way. When candidates receive structured guidance, realistic practice, and continuous feedback, their professional growth becomes sustained and unstoppable.

What it does

Momentum is an AI-powered hiring and career growth ecosystem built to bring structure, fairness, and intelligence to recruitment.

For candidates, Momentum:

Analyzes resumes beyond keyword matching to evaluate structure, clarity, and impact
Generates role-specific coding challenges and scenario-based questions
Conducts realistic AI mock interviews in a high-pressure simulation environment
Produces detailed performance reports with scores, strengths, weaknesses, and improvement suggestions

For recruiters, Momentum:

Enables job posting and candidate applications
Uses AI to screen resumes against job descriptions and generate fit scores
Supports interview scheduling across three modes:
- Face-to-face interviews with AI-powered proctoring
- Semi-AI interviews where recruiters provide questions and AI conducts the session
- Fully AI-driven interviews where recruiters specify only topic and difficulty

Each interview produces a comprehensive evaluation report, enabling faster and more data-driven hiring decisions.

How we built it

Momentum was built using a modern full-stack architecture.

Frontend: Next.js, React, TailwindCSS for a fast and responsive user experience
Backend: Node.js APIs with MongoDB for scalable data storage
Authentication: Firebase Authentication for secure login and role-based access control
AI Engine: Google Gemini API, powering resume analysis, problem generation, interview logic, feedback, and scoring
Development Environment: Antigravity IDE

To ensure interview integrity and realism, we built a Python-based desktop interview application using:

PyQt6 for the desktop UI
OpenCV and MediaPipe for computer vision and eye-tracking
Speech-to-Text and Text-to-Speech for audio analysis and interaction

The desktop app integrates seamlessly with the web platform, syncing interview sessions and results in real time.

Challenges we ran into

One of the biggest challenges was generating AI feedback that felt meaningful, fair, and actionable, rather than generic or repetitive. Designing scoring systems that candidates could trust and recruiters could rely on required careful iteration.

Ensuring interview integrity without harming user experience was another major hurdle. Additionally, synchronizing real-time data between a desktop application and a cloud-based web platform introduced complex system design and reliability challenges.

Accomplishments that we're proud of

We’re proud to have built a complete end-to-end hiring ecosystem that supports both sides of recruitment. Key accomplishments include:

A three-tier AI interview system
Detailed AI-generated interview reports and scoring
Resume-to-job description matching with explainable feedback
Integrated proctoring and behavioral analysis
Seamless integration between web and desktop platforms

Together, these features transform subjective interviews into measurable, transparent outcomes.

What we learned

Through building Momentum, we learned how to design AI systems that support human decision-making rather than replace it. We gained hands-on experience combining web development with computer vision, speech analysis, and large language models.

Most importantly, we learned that transparency, structured feedback, and fairness are critical to building trust in AI-driven hiring systems.