NudgeBox: The Ghost in Your Inbox That Haunts You Before a Recruiter Can Ghost You
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine What I Built NudgeBox is a ghost that lives in a job seeker's inbox. It quietly reads Gmail, finds interview invites and online assessments (HackerRank, Codility, CodeSignal, recruiter calls), and then haunts the user at T-7 days, T-1 day, morning-of, and T-1 hour . The last one is a voice note on…
NudgeBox is an AI-powered tool designed to help job seekers stay on top of their interview invitations and online assessments by alerting them at critical times. This small, privacy-focused agent quietly monitors the user's Gmail inbox and identifies important emails related to interviews and assessments from platforms like HackerRank, Codility, CodeSignal, and recruiter calls. It then discreetly sends reminders at key intervals - seven days before, one day before, the morning of, and one hour before the actual interview.
The inspiration behind NudgeBox came from a personal experience with a friend who missed an important recruiter screen due to a buried email and an odd timezone abbreviation. The developer wanted to ensure that such a missed opportunity would not happen again for other job seekers.
The core functionality of NudgeBox revolves around its ability to autonomously extract relevant interview and assessment information from the user's Gmail inbox. This is achieved without requiring any password access or modifications, ensuring that the user's inbox remains secure. The tool uses a zero-password authentication system based on OAuth PKCE, and all email content is processed locally using an open-weight model called Gemma 3, which runs independently on the user's machine using Ollama.
Once the necessary information is extracted, NudgeBox schedules reminders using Temporal, a workflow management system. These reminders are then delivered through various channels, such as Telegram, using ElevenLabs' text-to-speech technology. The entire process is designed to be resilient, with the ability to withstand disruptions or restarts without losing the scheduled reminders.
NudgeBox prioritizes security and privacy, employing AES-256-GCM encryption for storing refresh tokens and redacting sensitive information like phone numbers, SSN-like patterns, and tracking IDs before the model processes the data. The tool also implements a thorough threat model to ensure that it operates safely and securely within the user's environment.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
