# Project export: Thunder Apply

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: Cal Hacks 11.0
- Tagline: Sit back and relax. Let AI fine tune your job application and apply for you
- Devpost: https://devpost.com/software/thunder-apply-nxmgcq
- GitHub: not linked
- Video: https://www.youtube.com/embed/_Ce1etxc5Ps?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

The inspiration for Thunder Apply came from the frustration job seekers face when applying to multiple positions. The tedious and time-consuming process of filling out repetitive applications often discourages qualified candidates from pursuing opportunities. We recognized the need for a solution that could streamline this process, allowing job seekers to focus on preparing for interviews and career development rather than spending countless hours on application forms.

### What it does

Thunder Apply is an application that fully automates the job application process across various platforms. Unlike existing solutions that only partially automate the process, Thunder Apply: Parses and understands application forms from major applicant tracking systems (ATS) like Workday, Greenhouse, and Lever, as well as custom-built platforms. Utilizes a fine-tuned GPT-4 model to generate tailored responses to custom questions, ensuring each application is personalized and relevant. Automatically fills in all required fields, including complex forms and questionnaires. Submits applications on behalf of the user, requiring minimal intervention. Provides real-time updates on application status and progress.

### How we built it

We developed Thunder Apply using a combination of technologies: A Python based application for integration with job application websites. Playwright - Vision based technology to detect and fill the fields. A fine-tuned GPT-4 model trained on thousands of successful job applications to generate high-quality, context-appropriate responses.

### Challenges we ran into

Developing a robust system to recognize and parse the wide variety of custom application forms and questions across different platforms. Ensuring the AI-generated responses maintain a high level of quality and relevance across diverse industries and job roles. Balancing automation with user control to maintain the personal touch in applications when needed. Addressing potential ethical concerns regarding automated applications and ensuring compliance with various job board policies.

### Accomplishments we're proud of

Achieving a 95% success rate in accurately filling out complex application forms, including custom questions Reducing the average time spent on job applications by 90%, from 100 hours to just 10 hours for a typical job search

### What we learned

The importance of continuous learning and adaptation in AI models to keep up with evolving job application processes. The critical balance between automation and maintaining the human element in job applications. The vast potential of AI in revolutionizing not just job applications, but the entire recruitment process. The need for transparent and ethical AI practices in recruitment technology.

### What's next

Expanding our AI capabilities to include interview preparation and personalized career advice. Integrating with professional networking platforms to leverage connections and referrals. Developing partnerships with major job boards and ATS providers to enhance compatibility and reach. Implementing advanced analytics to provide users with insights into their job search performance and market trends. Exploring the possibility of a recruiter-facing version to streamline the hiring process from both ends.

## 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.
- 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.