InterHunt

Inspiration

Interview prep can feel overwhelming and isolating. You jump between practice questions, mock interviews, and advice online, but it’s hard to know what you’re actually good at or what to focus on. We wanted to make interview prep feel more engaging, less intimidating, and easier to reflect on, especially for students preparing together.

What it does

InterHunt is a pixel-art, time-based game where you play as a student navigating a map before an interview. Each location is an information node that challenges you with mock interview questions or interview-process trivia. Your answers are scored and you receive feedback, and if you struggle, the game recommends courses or topics to help you improve. The goal is to simulate interview pressure while turning mistakes into clear next steps.

How we built it

We built InterHunt as a lightweight, logic-driven game focused on gameplay flow and feedback. The core includes player movement, timed exploration, interactive challenge nodes, scoring, and response evaluation. We used pixel art to keep the experience approachable while prioritizing mechanics and learning over visuals.

To support meaningful feedback, we integrated the Gemini API to assess mock interview responses in different ways, such as clarity, relevance, and structure. When a player struggles with a challenge, we use the SFUCourses API to recommend relevant courses that could help strengthen those skills. We also integrated InternDB to provide insights about different companies, helping tie challenges back to real internship expectations.

We designed the system to be modular, so new challenge types and competitive features like multiplayer and leaderboards can be added without reworking the core game.

Challenges we ran into

One of our biggest challenges was balancing scope. We originally planned features like LeetCode-style problems, debugging challenges, multiplayer, and leaderboards, but had to prioritize a smaller, polished core experience. Designing meaningful feedback for open-ended mock interview responses was also tricky, especially under hackathon time constraints. Dealing with the rate limtis of Gemini's APIs was also a pain.

Accomplishments that we're proud of

We’re proud that we built a complete, playable experience with a clear learning loop. Players can move through the map, face real interview-style challenges, get scored, and leave with actionable feedback. We also designed the system to be easily extendable, so new challenge types and competitive features can be added later.

What we learned

We learned how important it is to scope realistically and focus on what delivers the most value to users. We also gained experience designing systems that blend learning with gameplay, and thinking about feedback not just as a score, but as guidance for improvement.

What's next for InterHunt

Next, we want to add multiplayer support so students can compete or collaborate with friends in real time, making the experience more social and engaging. We also plan to implement real coding challenges, like actual LeetCode-style submissions, so players can practice coding in a realistic way and get automated feedback. These additions will make InterHunt a more complete, interactive, and practical tool for interview preparation, while keeping the feedback and course recommendations that help students improve where they need it most.