{"slug": "my-friend-asked-for-interview-practice-so-i-built-an-ai-interviewer-that-runs", "title": "My friend asked for interview practice, so I built an AI interviewer that runs locally", "summary": "A developer built Mock Interview Partner, a locally-run AI mock interviewer that takes a resume and target role and generates tailored questions, follow-ups, strict 1-to-5 per-answer scoring and a final report with weaknesses and a practice plan. The tool runs entirely on a laptop using the open-weight llama3.2:3b model via Ollama on a 6 GB RTX 4050, so no resume or interview recording leaves the machine. The developer said the model initially over-scored weak answers until explicit score anchors and strict-grader instructions were added, and a friend preparing for placements reported the improved sample answers and per-question review were the most useful parts.", "body_md": "*This is a submission for the [Hacktoberfest Weekend Challenge: Build for a Friend](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01)*\n\nFRIEND is in placement season and told me one thing scares them most: SPECIFIC FEAR, e.g. \"I freeze when they ask about my own project.\" Paid mock interview tools cost money and want a full resume uploaded to someone else's server.\n\nSo I built **Mock Interview Partner**: upload a resume, pick a role, and it interviews you. It asks questions about your actual projects, pushes back on vague answers with follow-ups, scores each answer strictly from 1 to 5, and writes a report with weaknesses and a practice plan. It runs completely on a laptop.\n\n(Optional: a 30 to 60 second screen recording.)\n\nA free, private mock interviewer for placement season. Upload a resume, choose a target role, and get tailored questions, follow-ups, strict per-answer feedback and a final report. It runs entirely on your own laptop with an open-weight model, so nothing is sent to a server.\n\nBuilt for the Hacktoberfest Weekend Challenge: **Build for a Friend**.\n\nA resume contains a phone number, address, grades and email, and a mock interview records someone's honest mistakes. Neither belongs on a server you don't control. Running a local open-weight model means nothing leaves the laptop, and no internet is needed once the model is downloaded.\n\nOpen source also gives you:\n\n`llama3.2:3b` through Ollama, fully on a 6 GB RTX 4050\nThe flow is: resume text → structured profile → question plan → answer → score and feedback → optional follow-up → final report.\n\nEverything behavioural lives in plain text: the prompts, three interviewer personas and a `rubric.yaml` with score anchors.\n\n**What went wrong:** WRITE ONE REAL FAILURE. Ideas: the model gave 4 or 5 out of 5 to weak answers until I added explicit score anchors and told it to grade like a strict interviewer. Or the 7B model split between GPU and CPU on 6 GB of VRAM and was painfully slow, so I moved to the 3B model (X seconds per answer instead of Y).\n\nI ran a mock interview with FRIEND_NAME, who is preparing for placements, and asked for honest feedback afterwards.\n\nTheir first reaction was a simple **\"wow.\"**\n\nWhat they found most useful was the **improved sample answers and the review** after each question. When I asked what the tool showed them that they hadn't noticed, they said: *\"I missed too many things, and this app pointed them out. I improved my answer.\"*\n\nI also asked whether any scoring felt unfair, since a strict grader is only useful if it's fair. They said no, the feedback looked fair to them.\n\nTheir verdict on using it again before placements: *\"Yes, it will help me a lot.\"*\n\nThat last answer is what I built it for: a free place to practise as many times as they need, without a resume or answers going to anyone else's server.", "url": "https://wpnews.pro/news/my-friend-asked-for-interview-practice-so-i-built-an-ai-interviewer-that-runs", "canonical_source": "https://dev.to/abhishek_gupta_982095928c/my-friend-asked-for-interview-practice-so-i-built-an-ai-interviewer-that-runs-locally-2obb", "published_at": "2026-10-04 18:07:57+00:00", "updated_at": "2026-10-04 18:12:44.030182+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-tools", "ai-products"], "entities": ["Ollama", "llama3.2:3b", "Mock Interview Partner", "Hacktoberfest", "RTX 4050"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/my-friend-asked-for-interview-practice-so-i-built-an-ai-interviewer-that-runs", "markdown": "https://wpnews.pro/news/my-friend-asked-for-interview-practice-so-i-built-an-ai-interviewer-that-runs.md", "text": "https://wpnews.pro/news/my-friend-asked-for-interview-practice-so-i-built-an-ai-interviewer-that-runs.txt", "jsonld": "https://wpnews.pro/news/my-friend-asked-for-interview-practice-so-i-built-an-ai-interviewer-that-runs.jsonld"}}