top of page

AI Prototype building




AI Prototype Building



Project Duration:

4 months+

AI-supported candidate search 

AI-generated questions based on the job description 

Evaluation of the candidates 

Chat-guided pre-interview to select the candidates 

Alexa Young, CA

“Testimonials provide a sense of what it's like to work with you or use your products. Change the text and add your own."






This project aims to revolutionize the interview process by automating it with AI-generated questions and conducting chat-based interviews for candidate selection. This innovative approach is designed to save a significant amount of recruited working hours, streamlining the candidate selection process for the client.

Team: Paul-Louis Pröve, Marcel Bosse

The project encountered key challenges in preparing and structuring data to make it suitable for AI processing. This involved ensuring the data's relevance and accuracy to feed into the AI system effectively. Additionally, a significant challenge was in configuring the correct OpenAI prompts, which required precise calibration to generate relevant and appropriate interview questions tailored to each candidate and position.

To overcome these challenges, the project team collaborated with Azure Cognitive Search, leveraging its advanced capabilities for efficient data handling and preparation. They integrated a Retrieval-Augmented Generation (RAG) system, which enhanced the AI's ability to generate contextually relevant and accurate interview questions. Additionally, the team compiled insights and best practices from numerous AI projects, applying this accumulated knowledge to refine and optimize the interview automation process.

The project successfully utilized data from over 1.5 million applicants, enabling the AI system to identify suitable candidates in under a minute. This efficiency was further enhanced by conducting substantial chat interviews, which significantly expedited the candidate selection process. Additionally, a comprehensive database of AI-generated interview questions was compiled, creating a valuable resource for future projects and further streamlining the recruitment process.

  • Azure Cognitive Search 

  • Streamlit

  • Gradio

  • OpenAI API

bottom of page