# Project export: ColdPitch

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 2025
- Tagline: ColdPitch uses AI to help master cold outreach and nail interviews. From personalized cold emails to smart interview prep, it’s your all-in-one tool to get noticed and get hired—without the guesswork.
- Devpost: https://devpost.com/software/coldpitch
- GitHub: not linked
- Demo: https://coldpitch-v2-694260220645.us-west1.run.app/
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

Many interviewees/future job applicants are not confident in their abilities and feel nervous for their first job interview fearing rejection. Practicing with family or friends is very different from the real interview largely because they are on your side and want to see you succeed. Having an AI assistant to objectively review your interview skills can go a long way in building up confidence

### What it does

The app gives users a chance to run their cold-email/interview by an objective AI to give them a score. This gives them the chance to iteratively improve themselves.

### How we built it

We built the app using React and the Gemini API

### Challenges we ran into

Our biggest challenge when working on the project was designing system prompts that would consistently give us AI responses that we approved of

### Accomplishments we're proud of

We were proud of completing out first AI app in such short a time frame and have gained skills in react and API usage as a result.

### What we learned

Throughout the project we learned to use Gemini's API as well as improved our skills in React.

### What's next

We would need to build upon ColdPitch by fine-tuning the AI on previous job interview transcripts or examples to give more specific results beyond what we got through the use of system prompts. We would also implement company specific interviews that would allow for more tailored interviews. We would also improve the voice interview my replacing the text to speech voice with a voice API.

## 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.
- Google Gemini (technology) — claimed on Devpost, not found in the code
- React (technology) — 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.