Hey HN community!<p>As a software engineer who took an unconventional path (bootcamp graduate in late 2021), I've spent the last 3 years in the 9-5 grind, constantly dreaming of building something meaningful. After watching my brother struggle with interview anxiety, I built Acedit: an AI interview coach.<p>What it does:<p>- Provides real-time, personalised prompts during online interviews<p>- Parses job listings for targeted practice questions and answers (from popular job listing websites LinkedIn, indeed, etc…)<p>- Offers mock interview simulations<p>Tech stack: NX Monorepo, Express, React, Playwright (e2e testing), Supabase (auth/DB)<p>What sets it apart:<p>- Chrome extension format (less intrusive than a PWA)<p>- Ability to seamlessly parse info from the users active tab (allowing for quick and easy extraction of listing information)<p>- Free tier with unlimited live interviews (uses gpt-4o mini)<p>Biggest challenges:<p>- Balancing helpfulness with ethical use (it's a coach, not a cheat sheet)<p>- Optimising AI response time for real-time use<p>- Building accurate "Question Detection" using NLP<p>I'd love your feedback on:<p>- Ethical considerations - how to ensure proper use?<p>- Performance optimisation ideas<p>- Potential expansions (e.g., LinkedIn lead generation, more in-depth practice modes)<p>Thanks HN! Excited to hear your thoughts and answer any questions.