Swiggy Saathi - A Senior Friendly Food & Grocery App
Swiggy Saathi is an AI-powered food ordering app designed specifically for elderly users aged 60+ who are excluded from mainstream food delivery platforms due to cognitive overload, tech anxiety, and lack of dietary awareness in existing products.
The core insight from primary research was that elderly users do not lack the desire to order food independently they lack a product designed around their mental model, not a younger user's.
Swiggy Saathi solves this with a 3-tap ordering flow, automatic dietary filtering set once during onboarding, a one-tap re-order for familiar meals, and plain-language order tracking removing every friction point that causes elderly users to abandon the experience or ask for help.
The value it generates is independence: users can order food without depending on a family member, and families get peace of mind knowing their elderly parent has a safe, simple way to eat well when alone.
15 May 2026
Keywords
AI Usage
Research and synthesis: Used Claude to analyse raw interview notes from 5+ user conversations, surface recurring patterns, and generate a structured pain point map. What would have taken a day of manual synthesis took under two hours with AI assistance. Ideation and prioritization: Used Claude and NotebookLM to stress-test feature ideas against the research findings, identify which features directly addressed the Jobs to Be Done, and pressure-check the MVP scope before writing the PRD. PRD and documentation: Used Claude to draft the initial PRD structure and refine problem statements, user personas, and success metrics into crisp, recruiter-ready and stakeholder-ready language. UI and design: Used Lovable to generate the full mobile-first UI from a detailed product prompt specifying large text, high-contrast colors, minimum touch target sizes, and a linear single-action-per-screen flow. Design decisions were product-driven, not aesthetic-driven. Coding and deployment: Lovable generated the entire frontend codebase. Claude was used to debug component logic, refine the dietary filter functionality, and ensure the re-order flow worked correctly end to end. Deployed to Vercel and Netlify in under 30 minutes.
