# Zaka

- **Event:** [RAISE Summit Hackathon](https://cerebralvalley.ai/e/raise-summit-hackathon)
- **When:** Jul 4 at 9:00 AM – Jul 5 at 7:00 PM (GMT+2)
- **Where:** Paris, France
- **Team:** [Chairul Akmal](https://cerebralvalley.ai/u/chairulakmal), [Fatma Janna](https://cerebralvalley.ai/u/fatjan)
- **GitHub:** https://github.com/chairulakmal/raise-zaka
- **Demo video:** https://www.youtube.com/shorts/Gp8HhXpmFII
- **Gallery:** https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/115

Zaka certifies JLPT question difficulty empirically instead of asserting it. A governed pipeline retrieves grounded vocabulary, generates a question, gates it deterministically, audits it, then tests it live on four simulated JLPT learner levels (N5-N2) — if the difficulty gradient is wrong, it retrieves again and retries under policy before certifying. Built for the Vultr track: every model call runs on Vultr Serverless Inference.

## More from RAISE Summit Hackathon

- [morph](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/112)
- [PepperCandy](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/113)
- [X-Arc](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/114)
- [T2MV](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/116)
- [MAYDAY](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/117)
- [TOSCO](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/118)

---

Markdown version of https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/115. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt