Thunder Apply

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 that 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 for Thunder Apply

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.

Built With

• gpt-4o
• openapi
• playwright
• python