Pani Kaisa Hai

Pani Kaisa Hai — Hindi for “how is the water?” — is a community early-warning app for drinking-water safety in Indian neighbourhoods. The premise is deceptively simple: before you take the first bite of your golgappa, you ask whether the pani — the flavoured water it is filled with — is clean. The app lets residents report what they notice about their tap water (smell, colour, taste, grit, or illness at home), scores those signals against India’s drinking-water standard (IS 10500), and shows a live “golgappa map” where every neighbourhood carries a label named after what happens to a golgappa: Crisp (all fine), Soggy (something is off), Phoot gaya (burst — contaminated), or Fresh batch (fix recorded, area recovering).

The sharpest design idea is who gets the final say. The app never lets a machine declare water unsafe by itself: once signals reach a threshold (six points, or a positive bacteria test), a case is raised but stays locked until a named health worker reviews the evidence and confirms or dismisses it — with a reason put on the record. As the site puts it: “A machine can raise a case. Only a person can declare the water unsafe.” A public “Shake the golgappa” simulator lets anyone pile on signals and watch the scoring logic work — including the one step the software will never take on its own.

The build is unambiguously vibe-coded. The author built the whole app with Claude Code over about seven sessions between 19 September and 4 October 2026, kept a build log the entire way — including the parts that went badly — and wrote the process up for the Sanity “Vibe-Code Something Strange” challenge. BUILD_LOG.md is public in the GitHub repo (github.com/Reet24-del/pani-kaisa-hai), which also ships 33 tests. Declared stack: Next.js 16 (App Router), TypeScript, Sanity Studio v6, and Leaflet + OpenStreetMap for the map.

The demo currently online runs on sample data: the author honestly labels the site “Sample data — demo build” throughout, with an Indore neighbourhood set used for illustration. It is live and fully functional — the reporting flow, the live status ticker, the map and the simulator all render and work.