I'm a Tunisian high-school student (Sciences de l'Informatique, bac 2028) building applied-AI and health tools that know their limits. I work on applied AI, health informatics, agriculture, and climate risk β small systems with clear limits and readable behavior.
π¬ Honesty engineering β the boy who teaches machines to say: I don't know. My research and my projects ask the same question: what does a system owe the people who trust it, when its data cannot be trusted?
Python Β· JavaScript Β· Flask Β· React Β· Vite Β· SQLite Β· Git β small stack, shipped often.
- π§οΈ Rain2Risk β transparent relative flood-risk screening with documented data limits and tests. Live: rain2risk.vercel.app
- πΎ CropGuide AI β agricultural decision support with explicit uncertainty, data audits, and tests.
Honest limits, printed on the label: both are exploratory software. CropGuide AI is not a substitute for agricultural expertise; Rain2Risk is a screening score, not an official warning or forecast.
π More builds β click to open
| Project | What it is |
|---|---|
| Bakery ERP Pro | Bakery management demo β stock, sales, production (a demo project, not production ERP) |
| AI Health Assistant | Health-assistant prototype built on careful, limited claims |
| Clinique | Clinic management system |
| Finance Platform | Personal-finance tracking platform |
AI-Based Clinical Decision-Support System Robustness Under Unreliable Patient Data β a narrative review and thematic synthesis, published as a preprint on Zenodo in 2026. Fifteen studies, six robustness themes, one conclusion: a clinical AI that cannot say "I don't know" is not safe yet.
Bias Bounty: Mapping Equity Challenge on Zindi (Humane Intelligence Γ Radiant Earth) β estimating Overture Maps coverage gaps across 9,794 US census tracts with a fully documented, reproducible, no-training methodology. The challenge closes 31 Oct 2026; the final ranking rests on a private leaderboard.
- π Public RMSE 0.1966 β 0.1042 across five logged submissions β the honest route: a rule-based index, a wrong denominator found and fixed, then shrinkage toward regional means.
- π Zindi badges earned so far β and ranked #9,686 among 100,000+ AI builders on the platform:
First Steps Β· Go-Getter Β· Zindian
- π The complete methodology write-up (including the failed first version, and why) goes public with the project repo once the challenge closes.π Verified highlights β click to open
- AI in Healthcare Specialization Β· Stanford Online (Coursera)
- AI in Government Β· Oxford SaΓ―d






