About SaafHawa
Pakistan's cities sit near the top of every "most polluted air" list in the world, and the people who pay the price are the ones least equipped to read the data — parents deciding on a school run, an elderly relative breathing through a smoggy morning, a pregnant woman, a delivery rider working outdoors all day, anyone with asthma or pollen allergy. SaafHawa takes the open AQI data that already exists and turns it into a clear, per-household, bilingual decision — in the language people actually think in.
Hackathon themes
Uses AI to tackle a daily public-health challenge — air pollution — and improve how life-protecting guidance reaches ordinary citizens.
Takes public, open air-quality data that most people can't interpret and makes it transparent, actionable, and accessible in the language they actually think in.
How we built it
The AQI exists. The gap is making it actionable. AI shines exactly here — turning a number into safe, personalised, plain-language advice.
Urdu isn't a translation toggle. The model emits EN + UR side by side, rendered in proper Nastaliq.
Open APIs go down, free tiers rate-limit, Pakistani Wi-Fi is unreliable. Every layer has a fallback so guidance always loads.
Backend and frontend speak through a strict Pydantic schema. The LLM is locked to JSON mode against it.
Open AQI data, free-tier LLM, SQLite. Anyone in Pakistan can fork it and run it for their own city.
Planned WhatsApp / SMS delivery puts guidance on any phone — no app, no smartphone required.
Team
Built end-to-end during the hackathon — backend, AI layer, bilingual frontend, deck, and demo.
Hackathon
In collaboration with Grey Software, Scrimba and FAST NUCES Islamabad.
The fastest way to understand SaafHawa is to try it on today's air.
Launch the app →