Inspiration As students and fresh graduates, we noticed that while job listings are easy to find, understanding what employers actually want is much harder. Job descriptions are often long, inconsistent, and spread across multiple platforms, making it difficult to know which skills matter and how to prepare for a role. We wanted to build something that doesn’t just show jobs, but guides students through their career journey — from understanding themselves to applying confidently.
What it does CareerPath is a platform that helps fresh graduates and job seekers find the right jobs, not just any job. Users can upload their resume, which is automatically analysed to extract technical skills, soft skills, certifications, languages, and experience. Based on this profile, CareerPath provides AI-driven career guidance, personalised skill roadmaps, and upskilling recommendations. Job listings are presented with clear skill requirements and matched against the user’s profile, allowing users to quickly understand their fit and identify gaps. Users can then apply to jobs and track their applications and interviews in a single dashboard.
How we built it We built CareerPath as a full-stack web application. On the frontend, we focused on a clean and intuitive user experience that guides users from profile creation to job application. On the backend, we used Supabase as a backend-as-a-service to handle authentication, PostgreSQL data storage, Row Level Security (RLS), and automatic profile creation through database triggers. AI agents are used to analyse resumes and job descriptions, extracting structured information such as skills, education, certifications, and experience. This structured data powers profile analysis, skill roadmaps, upskilling recommendations, and skill-based job matching.
Challenges we ran into One of our biggest challenges was converting unstructured text — such as resumes and job descriptions — into structured, reliable data. Ensuring that extracted skills and requirements were consistent and meaningful required careful prompt design and iteration. We also had to design a secure data model that supports multiple user flows while ensuring proper access control. Implementing Row Level Security policies correctly was critical to prevent users from accessing or modifying data they shouldn’t see.
Accomplishments that we’re proud of We’re proud that CareerPath goes beyond a typical job board. Instead of just listing jobs, we built a guided system that connects self-assessment, learning, and job application into a single flow. In a short hackathon timeframe, we successfully implemented resume analysis, AI-driven career guidance, skill-based job matching, and a centralized dashboard for tracking applications and interviews. The platform is functional end-to-end and demonstrates how AI can meaningfully support career planning.
What we learned Through this project, we learned how to design AI-powered systems that work with real-world, messy data. We also gained hands-on experience building secure full-stack applications using Supabase, PostgreSQL, and Row Level Security. Most importantly, we learned the value of designing from the user journey first — focusing on clarity, guidance, and actionable insights rather than just features.
What’s next for CareerPath If we continue developing CareerPath, we plan to improve the accuracy of AI skill extraction, expand upskilling recommendations with real course integrations, and enhance job matching with scoring and ranking. We also want to support more user types, such as employers and career switchers, and introduce analytics that show job market trends and in-demand skills. Ultimately, our goal is to make CareerPath a comprehensive career guidance platform that supports users throughout their professional journey.
Log in or sign up for Devpost to join the conversation.