# Project export: InterviewIQ

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: UC Berkeley AI Hackathon 2026
- Tagline: InterviewIQ is an AI mock interview coach. You pick a role, difficulty, and length, answer real questions, and get instant scored feedback plus a personalized practice plan.
- Devpost: https://devpost.com/software/interviewiq-kcam9v
- GitHub: not linked
- Video: https://www.youtube.com/embed/6Zap8Q641W4?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

With so many of us being college students getting ready to transition into the real world. Most of us do not have any real interview experience which separates us from each other beyond a technical scope. This project is directly applicable to people in the real world which makes it a great tool.

### What it does

It asks you for your interview type which there are three options, "Software Engineering", "Behavioral", or "Product Management." You also select the difficulty of the questions and how many questions you want to be asked. After submitting a response it gives you your strengths, areas to improve, sample strong answer, and a grade for your response.

### How we built it

I built it using a lot of help from Claude Code, this is my first time having the chance to use it in a hackathon so I decided to experiment with its capabilities after my original idea was failing.

### Challenges we ran into

This is a unique personal challenge to me, but my flight kept on being delayed on my way to the bay so I had minimal time to build this entire project and built it all in the airport. Beyond time crunches it was hard to come up with an idea that sounded unique while also being applicable to everyday life. After finally settling on the idea, the execution was not too bad.

### Accomplishments we're proud of

I am really proud of the fact that I overcome all my personal obstacles to actually build this project. I am really exhausted from external circumstances so just finishing something that I probably will use in my own life after this hackathon is something to be proud of for me.

### What we learned

I learned that Claude code is really powerful and combining it with LLMs really expands how impactful it can truly be. I also learned to work on the fly and in uncomfortable situations.

### What's next

I want to make the front end look more consumer friendly and perhaps add some roadmap like LeetCode to make it more progressive.

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- JavaScript (language) — claimed on Devpost, not found in the code
- Python (language) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.