PrepPal: How I Built an Adaptive, Open-Source AI Mock Interviewer for My Anxious Batchmate
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built Every placement season on campus, the same story unfolds: brilliant engineers who can write flawless code freeze up the moment an interviewer asks them to explain concepts out loud. My close friend and college roommate is one of those engineers. Despite knowing distributed systems and algorithms inside…
This story recounts the creation of PrepPal, an AI-powered mock interviewer designed to help anxious engineers prepare for technical interviews without the pressure of judgment or high costs. The author, scar3max, built PrepPal for their college roommate who struggled with interview anxiety despite having deep knowledge in computer science fundamentals.
PrepPal is an adaptive, conversational mock interviewer that adjusts its questioning based on the candidate's real-time performance, offering immediate feedback and analytics to guide preparation.
The key features of PrepPal include a natural, concise dialogue format that mimics real interview conditions, behavioral and hesitation detection to refine the questioning based on the candidate's responses, and dynamic difficulty adjustment that increases the complexity of questions if the candidate is excelling or pivots to a different topic if they're struggling.
The system provides real-time feedback through badges and detailed analytics via a Plotly dashboard, giving candidates insights into their performance trends and areas for improvement. Built with a hybrid Edge-Cloud architecture utilizing an open-source Small Language Model (SLM) and a cloud-based Groq API, PrepPal ensures zero anxiety and complete privacy by running inference locally on a laptop, eliminating the need for internet dependency in drafting responses.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
