AI-Assisted Job Application Tracker

• 

  this is kanban board

• 

  this is application creation baord

Inspiration

Job searching is often messy and time-consuming. Tracking applications across different platforms and tailoring resumes for each role becomes repetitive and inefficient. I wanted to build something that simplifies this entire workflow using AI and makes job hunting more structured and intelligent.

What it does

AI-Assisted Job Application Tracker is a Kanban-based web app where users can manage their job applications visually. Users paste a job description, and AI automatically extracts key details like company, role, skills, and location. It also generates tailored resume bullet points for that specific job. Users can drag and drop applications across stages like Applied, Interview, Offer, and Rejected.

How we built it

We built the frontend using React with TypeScript and Tailwind CSS for a clean, responsive UI. The backend is powered by Node.js, Express, and MongoDB with Mongoose for data storage. Authentication is handled using JWT and bcrypt. The AI layer uses Gemini API with structured JSON outputs to reliably parse job descriptions and generate resume suggestions. AI logic is separated into a service layer for clean architecture.

Challenges we ran into

One major challenge was ensuring the AI always returned consistent structured JSON, especially for varied job descriptions. We solved this using strict prompting and validation logic. Another challenge was managing state consistency while implementing drag-and-drop across Kanban columns without breaking UI sync with the backend.

Accomplishments that we're proud of

We successfully integrated AI in a meaningful way beyond simple chat responses—turning unstructured job descriptions into structured, actionable data. We also built a smooth drag-and-drop Kanban system with persistent backend storage and clean authentication flow.

What we learned

We learned how to design reliable AI-powered backend services, structure prompts for predictable outputs, and handle real-world UI state complexity. We also improved our understanding of TypeScript best practices, API architecture, and MongoDB data modeling.

What's next for AI-Assisted Job Application Tracker

Next, we plan to add analytics dashboards for application insights, smart reminders for follow-ups, resume export features, and improved AI personalization based on user history. We also aim to introduce collaboration features and mobile optimization.

Built With

• gemini
• mern
• tailwind
• typescript