Prep Buddy: an AI interview coach for my classmate that runs on his laptop with the Wi-Fi off

A developer built Prep Buddy, an offline mock-interview coach that runs entirely on a laptop using Google's Gemma 3 4B and EmbeddingGemma models via Ollama, with no API keys, accounts, or internet connection required. The tool asks campus-placement questions, grades typed answers against expected interview points, tracks weak topics for follow-up, and reports cold-start latencies of roughly 41 seconds for question generation and 25 seconds for grading on an Apple M2 with 8 GB of RAM. Classmate Aman said, "after answering the questions, I was provided with instant feedback and it helped me to identify my weak areas.

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend https://dev.to/challenges/hacktoberfest-weekend-2026-10-01 Aman is my classmate. We're both in final-year B.Tech, and like everyone in our batch he's preparing for campus placements: SDE-1 roles, which means technical rounds on DSA, DBMS, Operating Systems, Networks and OOP, plus an HR round. When I asked him how his prep was going, he wasn't sure. He was putting in the hours, but he couldn't tell which topics were actually weak. Nobody was asking him questions and telling him what he'd missed, so he kept revising the topics he was already comfortable with. The usual answers didn't fit him either: So I built Prep Buddy : a mock-interview coach that runs entirely on his laptop . It asks him a placement question, grades his typed answer against the points a real interviewer listens for, tells him what he missed, and remembers his weak topics so the next question goes after them. ₹0 to run · no API keys · no account · works with Wi-Fi off · his answers never leave his laptop A practice session works like this: After a few sessions, the dashboard answers the question he couldn't: where should I spend my next ten minutes? “What I liked about Prep Buddy was that after answering the questions, I was provided with instant feedback and it helped me to identify my weak areas. It helped me to know about my strengths and weaknesses prior to the interview.” The Wi-Fi is off in this recording. Every question, grade and summary comes from Gemma running locally on my Apple M2 laptop with 8 GB of RAM. There's no hosted link, on purpose. Hosting Prep Buddy on a server would break the one promise it makes: your answers stay on your laptop. The repo below runs on any 8 GB+ machine. The badge in the top-right corner says AI ready only when the database is up, Ollama is running and both models are downloaded. If something is missing, it shows the exact command to fix it for example ollama pull gemma3:4b instead of an error page. Machine: Apple M2, 8 GB Chat model: Gemma 3 4B Question bank: 56 questions across 7 topics | Step | Cold | Warm average | |---|---|---| | Next question | 41.15 s | 20.37 s | | Grade answer | 25.50 s | 14.81 s | | Session summary | 23.81 s | 15.08 s | For the golden-answer test, all 5 questions passed the required Excellent Average Wrong ordering. The prompt-injection test scored 2/10 and was classified as weak. An offline, private mock-interview coach for campus placements, powered by Google Gemma running on your own laptop. Built for Aman for the DEV Hacktoberfest Weekend Challenge: Build for a Friend https://dev.to/challenges/hacktoberfest-weekend-2026-10-01 . ₹0 to run · no API keys · works with Wi-Fi off · your answers never leave your laptop ▶️ Demo video : youtu.be/TgRr7m U FE https://youtu.be/TgRr7m U FE Every model call goes to Ollama https://ollama.com … The setup is three steps: start Ollama and pull the two models, run docker compose up for the database, then npm run dev . The README has the full commands. The repo also has the PRD, the architecture, the API reference, the AI design notes and the test results in docs/ . The code is MIT-licensed. The open-source AI at the core: | Piece | What it does in Prep Buddy | |---|---| | Gemma 3 4B open-weight, 3.3 GB via Ollama | Rewords questions, grades answers, writes the session summary | | EmbeddingGemma 622 MB, 768-dim vectors via Ollama | Turns questions and "what you missed" into vectors |