{"slug": "i-finally-finished-my-ai-interview-coach-it-only-took-me-getting-rejected-to", "title": "I Finally Finished My AI Interview Coach (It Only Took Me Getting Rejected to Care)", "summary": "A developer built an AI interview coach that runs entirely in the browser with no backend, accounts, or subscriptions, requiring only a free API key. The tool conducts full mock interviews across behavioral, technical, and system design modes, asks follow-up questions, scores responses on five dimensions, and generates a study plan. The developer reduced the crash rate from ~30% to ~2% and expanded AI provider support from one to four by leveraging Copilot for boilerplate code while handling system prompts and session flow design independently.", "body_md": "*This is a submission for the GitHub Finish-Up-A-Thon Challenge*\n\nAn AI interview coach that runs in your browser. No backend. No accounts. No subscriptions. You bring a free API key, paste your resume and the job description, pick a mode (behavioral, technical, system design, whatever), and it runs a full mock interview. Asks follow-ups, scores you on 5 dimensions, gives you a study plan at the end. I built the first version for the Gemma 4 DEV.to Challenge last month. It kinda worked. But I wouldn't have used it myself, and that bothered me. **Live:** [hajirufai.github.io/gemma4-interview-coach](https://hajirufai.github.io/gemma4-interview-coach/)\n\n**Repo:** [github.com/hajirufai/gemma4-interview-coach](https://github.com/hajirufai/gemma4-interview-coach)\n\n```\nBefore After\nLines of code 792 1,367\nAI providers 1 4\nVoice support Nope Mic + speaker\nError recovery Pray Auto-retry + backoff\nAPI validation Nope Test button\nDefault model 12B 31B\nCrash rate in sessions ~30% ~2%\n```\n\nI'll be honest about where Copilot carried its weight and where I turned it off. **Where it saved me real time:**\n\nThe Speech Recognition API has a bunch of browser-prefix nonsense (`webkitSpeechRecognition`\n\nvs `SpeechRecognition`\n\n). I typed `function initVoiceInput`\n\nand Copilot filled in the whole setup — event handlers, interim results, confidence thresholds. I tweaked the auto-stop timing and UI hooks, but the boilerplate was right on first try. Same story with the multi-provider fetch calls. After writing the Google AI Studio integration, Copilot predicted the OpenRouter request format almost perfectly when I started the next function. Just needed to adjust a couple headers. And CSS animations — the mic pulse effect, dark mode transitions, the glass morphism stuff. Copilot's suggestions were honestly better than what I'd write by hand. It knows the modern patterns. The retry-with-backoff logic was another clean one. I typed `async function callWithRetry`\n\nand got exponential backoff with proper error classification (retry 500s, fail fast on 401s) without spelling it out. **Where I ignored Copilot completely:**\n\nSystem prompts. The interview coach personality, scoring rubric, how it gives feedback — that needed careful thinking about what makes a good mock interview. Copilot's suggestions were generic motivational speaker stuff. Not useful. Session flow decisions too. When to show the mid-session scorecard, how to handle conversation context across questions, when to auto-scroll — these need design thinking, not autocomplete. **My honest take:** Copilot didn't write this app. But it cut out maybe 40% of the typing on the parts where I already knew what I wanted. The activation energy to *come back* to an old project is the hardest part. Having Copilot handle the boring bits meant I could focus on the decisions that actually mattered. ---\n\nTry it: [hajirufai.github.io/gemma4-interview-coach](https://hajirufai.github.io/gemma4-interview-coach/). All you need is a free key from [Google AI Studio](https://aistudio.google.com/apikey) — takes 30 seconds. If you're prepping for interviews, give the voice mode a shot. Talking through answers out loud is a completely different experience than typing them. Let me know which mode you found most useful 👇", "url": "https://wpnews.pro/news/i-finally-finished-my-ai-interview-coach-it-only-took-me-getting-rejected-to", "canonical_source": "https://dev.to/thyalpha001/from-hackathon-prototype-to-production-app-how-i-finished-my-ai-interview-coach-4aob", "published_at": "2026-06-03 12:38:12+00:00", "updated_at": "2026-06-03 12:42:15.989880+00:00", "lang": "en", "topics": ["ai-tools", "ai-products", "large-language-models", "generative-ai", "artificial-intelligence"], "entities": ["Copilot", "Gemma 4", "DEV.to", "GitHub", "Speech Recognition API"], "alternates": {"html": "https://wpnews.pro/news/i-finally-finished-my-ai-interview-coach-it-only-took-me-getting-rejected-to", "markdown": "https://wpnews.pro/news/i-finally-finished-my-ai-interview-coach-it-only-took-me-getting-rejected-to.md", "text": "https://wpnews.pro/news/i-finally-finished-my-ai-interview-coach-it-only-took-me-getting-rejected-to.txt", "jsonld": "https://wpnews.pro/news/i-finally-finished-my-ai-interview-coach-it-only-took-me-getting-rejected-to.jsonld"}}