InterviewPrep

💡 Inspiration

Preparing for interviews is frustrating and inefficient. Most candidates rely on generic interview questions that don’t reflect the actual role they’re applying for, while realistic mock interviews are expensive, time-consuming, or inaccessible. We were inspired by the gap between how people prepare for interviews and how interviews actually happen. We wanted to create a tool that makes interview practice personalized, realistic, and accessible to everyone.

How We Built It

InterviewPrep allows users to upload a job posting and their CV, which are analyzed to generate tailored interview questions specific to the role and the candidate’s background. We then simulate a real interview experience using a live AI avatar that conducts a mock interview in real time.

The focus was on creating a smooth, end-to-end experience that feels as close to a real interview as possible.

What We Learned

Throughout the hackathon, we learned a lot about integrating real-time communication technologies and managing live audio and video streams. We also gained experience designing AI-driven interactions that feel natural and engaging, rather than scripted. Most importantly, we learned how critical it is to balance technical ambition with usability and reliability under tight time constraints.

Challenges We Faced

One of the biggest challenges was integrating real-time video and audio while maintaining a smooth user experience. Managing authentication, environment configuration, and live streaming under hackathon time pressure required rapid debugging and iteration. We also had to make careful trade-offs between feature completeness and stability to ensure the core experience worked reliably during the demo.

Impact & Next Steps

InterviewPrep transforms interview anxiety into confidence by helping candidates practice smarter and more realistically. With more time, we’d love to add performance feedback, answer scoring, and different interviewer difficulty levels to further enhance the experience.

Built With

• css
• docker
• html
• javascript
• python
• react
• typescript