Kitna? Point your camera, know its worth

The problem. Nearly everyone in India has things they no longer use, and two questions stop the sale. What is it actually worth right now, and where do I sell it for the best return? Listings go stale, condition changes everything, and prices are scattered across Cashify, Quikr, Facebook Marketplace and WhatsApp groups with no way to compare them. Who it's for. People in India decluttering or upgrading, who know what they own but have no idea what it is worth, how to price it, or how to defend that price to a buyer. What Kitna? does. Point your camera at an item. On-device detection frames it in the live viewfinder and crops it, then a cloud vision model identifies the item and grades its condition, naming the specific wear it can see in your photo. Bright Data's SERP API pulls live listings from Indian marketplaces, and those real comps set both the resale range and its confidence band. You get a recommended sales channel, a ready-to-paste marketplace listing, and a Mol-bhaav haggling script with your asking price, your walk-away floor, and two Hindi-English counter-lines. Every number traces to evidence. The condition grade cites what the model actually saw. The price cites listings you can click. When no real comps come back, the app says so plainly and labels the figure an estimate. It never presents a price as live unless real listings back it. How native.builder was used. The Product Architect wrote the PRD from a plain-language spec. The Builder agent generated the Vite, React and TypeScript application, the design system, the camera capture hook and every screen, provisioned Supabase, and deployed the Edge Functions that keep all API keys server-side. The QA agent caught two dead-end bugs during live browser testing. External services. AI/ML API for vision with structured JSON output, Bright Data SERP API for live India comps, Speechmatics for voice, Supabase Edge Functions for secrets and runtime, and TensorFlow.js for on-device detection.