Inspiration

Hackathon projects are often judged under tight deadlines, with judges having to review numerous submissions, understand different technologies, and verify project claims. We wanted to make this process more structured, transparent, and reliable. This inspired us to build NEMO-JUDGE.

What it does

NEMO-JUDGE is an AI-powered hackathon evaluation platform that assists judges in reviewing submissions. It uses structured evaluation criteria to assess projects, examine supporting evidence, identify missing information, and support reproducibility checks. Its goal is to make project evaluation faster, more consistent, and evidence-based.

How we built it

We designed NEMO-JUDGE around a clean evaluation workflow, with dedicated sections for submissions, judging criteria, project analysis, and reproducibility. We focused on creating an intuitive interface that presents complex evaluation information clearly. We also explored how AI models and structured evaluation processes could assist human judges rather than replace their decisions.

Challenges we ran into

One of our biggest challenges was figuring out how to evaluate projects across different domains without relying entirely on subjective opinions. We also had to think about how to distinguish actual technical evidence from unsupported claims, while keeping the evaluation process simple enough for judges to use.

Accomplishments that we're proud of

We are proud to have developed a concept that addresses a real problem in hackathon evaluation. Building NEMO-JUDGE pushed us to think beyond a typical AI chatbot and design a practical platform focused on transparency, verification, and structured decision-making.

What we learned

We learned how to approach AI as part of a larger product rather than just a standalone feature. We also gained experience in designing evaluation workflows, thinking about evidence-based assessment, and building a user-friendly interface for a complex problem.

What's next for NEMO-JUDGE

We envision NEMO-JUDGE evolving into a complete hackathon evaluation ecosystem, with deeper repository analysis, automated testing, stronger reproducibility verification, customizable judging rubrics, and integrations with hackathon platforms. Our long-term goal is to help make technical project evaluation more transparent, scalable, and trustworthy.