betterATS

• 

  cover

• 

  landing page

• 

  dashboard

• 

  creating new job post

• 

  demo job

• 

  job description

• 

  all applicants

• 

  demo application

• 

  demo application 2

Inspiration

We wanted to modernize how applicant tracking systems work. Many existing ATS platforms rely heavily on document structure and keyword matching, often overlooking qualified candidates because of formatting differences. Our motivation was to create a smarter, fairer system that understands candidate potential through context rather than templates.

What it does

betterATS helps recruiters identify the right candidates efficiently. It uses AI to analyze resumes, extract key experiences and skills, and present them in a standardized summary. Recruiters can also view integrated video responses, allowing them to assess communication skills and thought processes before scheduling interviews. This creates a more accurate first impression and saves time in early screening. betterATS makes the applicant take a two minute video interview tailored for the company.

How we built it

We built betterATS using Next.js, React, TypeScript, Tailwind CSS, HTML5, and Supabase Auth. The backend focuses on AI-driven text analysis that interprets resumes contextually and structures information into consistent profiles. The frontend delivers a simple and responsive interface for recruiters to review candidate data and video submissions seamlessly.

Challenges we ran into

The hardest part was understanding how existing ATS systems function since most commercial systems are not publicly accessible. We had to research how ranking, parsing, and scoring mechanisms typically work and design our own logic to achieve similar results.

Accomplishments that we're proud of

We built a working AI model that interprets resumes accurately regardless of layout or structure. Integrating video responses into the workflow also made the hiring process more dynamic and insightful. Creating a complete, end-to-end platform from parsing to candidate review, within limited time and resources was a major milestone for our team.

What we learned

We learned how complex recruitment systems are behind the scenes. Building an ATS from scratch gave us valuable insight into information extraction, ranking algorithms, and user experience in HR tech. We also learned the importance of designing AI systems that remain transparent and fair to all applicants.

What's next for betterATS

Our goal is to continue refining betterATS into a system that improves both recruiter efficiency and candidate fairness.

Built With

• html5
• machine-learning
• nextjs
• react
• supabase
• supabase-auth
• tailwind-css
• typescript