v1 build
Case study · Consumer AI · home and food

How we built TasteIQ Home.

A household kitchen planner that scans the fridge, plans meals per family member and briefs the cook by voice in their language.

See it live ↗Build something like this
Client
TasteIQ Home
Industry
Consumer AI · home and food
Market
Bengaluru and Delhi NCR, India
Engagement
New product from concept to pilot
Platforms
WhatsApp, a web app and an MCP server for AI agents
2 cities in the pilot, as stated on the site
What we delivered
Product strategyAI developmentWhatsApp integrationMCP server
The brief

The problem to solve.

Families with different diets, fasts, health conditions and a home cook spend daily effort deciding what to cook, what is running out and what to reorder.

“Your kitchen, on autopilot.”The promise TasteIQ Home makes to its users
Our approach

From brief to launch.

  1. 01

    Discovery

    Spent time with families running a home kitchen with a cook, special diets and fasts.

  2. 02

    Design

    Made WhatsApp the main interface so the whole family can use it without an app.

  3. 03

    Build

    Built fridge scanning, per-person meal plans, voice briefs to the cook and approval-gated restocking.

  4. 04

    Launch

    Opened a pilot to the first homes in two cities, with an MCP server so AI assistants can use it too.

The solution

What we shipped.

Fridge and shelf photo scanning to keep an inventory and estimate shelf life

Per-person meal plans from health needs, fasts, taste and protein goals

Voice briefs to the cook in their language, with text transcripts

Restock suggestions with pre-filled carts on quick-commerce apps, sent only after approval

Medication reminders from uploaded prescriptions, and a festival and fast calendar

Family access over WhatsApp, with no app to install

Where AI does the work

  • Photo recognition for pantry items
  • Meal planning with a “signals” view that explains each choice
  • Voice transcription and multilingual briefs
  • An MCP server so assistants such as Claude or ChatGPT can read the pantry and plan meals, with purchases requiring approval
Under the hood

Engineering choices.

Next.jsVercel
  • Vision and voice AI in a consumer product
  • Human approval before any purchase or message
  • WhatsApp as the main interface
  • Exposing a product to AI agents through MCP
Results

Where it is today.

StatusPilot in Bengaluru and Delhi NCR, free during the pilot

Figures as published by TasteIQ Home on tasteiq.in/home, 22 October 2026.

Next case study TasteIQ Foods → Meal subscriptions that pack breakfast, lunch and dinner from partner kitchens near a building into one delivery.

Want results like TasteIQ Home?

Tell us what you are building. Get a fixed scope and price in writing within 24 hours.

Prefer email? hello@v1build.com