# hungpixi

- **Event:** [Built with Opus 4.7: a Claude Code hackathon](https://cerebralvalley.ai/e/built-with-4-7-hackathon)
- **When:** Apr 21 at 12:00 PM – Apr 27 at 2:00 AM (EDT)
- **Where:** Online
- **Team:** [Hung Pham Phu Nguyen](https://cerebralvalley.ai/u/hungpixi)
- **GitHub:** https://github.com/hungpixi/career-os-hackathon-2026
- **Demo video:** https://drive.google.com/drive/folders/1YBokI8bG0-S4AY1q5c5GFKNp68XWBuwK?usp=sharing
- **Gallery:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/68

Career OS is an AI-assisted job application operating system built for real-world job seekers.

The core problem it solves is application chaos: people usually track jobs, tailor CVs, draft emails, follow up, and monitor outcomes across disconnected tools and manual steps. This leads to missed opportunities, low-quality applications, and no clear feedback loop.

Career OS turns that into one structured workflow with a human-in-the-loop safety model:
- Scan -> match -> score jobs
- Generate tailored CV artifacts (with quality checks and provenance)
- Draft job-specific outreach emails
- Require explicit human approval before sending
- Send in controlled batches with anti-spam safeguards (daily quota + company cooldown)
- Log all events for audit/debug/replay

In this project, we implemented a hybrid local + API-contract architecture so the UI remains stable while backend services can be upgraded later without rewriting screens. We also added normalized domain schemas for runs/items/artifacts/drafts/events and enforced idempotent transitions for review/approve/send.

---

Markdown version of https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/68. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt