0-to-1 AI Product · Built with Lovable

Family Meal Planner — Weekly Menu & Grocery Assistant

A weekly meal-planning assistant for families — turning "what's for dinner" into an auto-generated week of meals and a ready-to-shop grocery list, instead of a nightly decision made from scratch.

Role
Solo builder — problem to working prototype
Method
Problem discovery, meal-planning flow design, prompt engineering
Scope
Home life, weekly meal & grocery planning
The problem

"What's for dinner" is a decision families make from scratch, every single night

Most families don't lack recipes — they lack a system. Without a plan, dinner becomes a nightly negotiation, and grocery runs happen reactively, one missing ingredient at a time, instead of once a week with a real list in hand.

Solution

Family Meal Planner: a week of meals, decided once

PREFERENCES

Set once, respected every week

Dietary needs, family size and repeat favorites are captured once, so the plan doesn't ask the same questions every week.

AUTO-GENERATE

A full week, planned in one pass

The assistant generates a full week of meals from those preferences, replacing seven separate nightly decisions with one weekly one.

SHOPPING LIST

A grocery list that's actually ready to shop

The week's meals convert directly into a consolidated shopping list — no manually cross-referencing recipes to figure out what's missing.

Set prefs Generate week Shopping list Cook & eat
Prototype

A working app, not just a flow diagram

Family Meal Planner is built and live — preference setup, weekly generation and the shopping list all work end to end in the prototype below.

Live prototype — Family Meal Planner Open full screen ↗
Open interactive prototype ↗
Process

Started from a nightly decision, not a recipe database

Discovery
Problem discovery — used Claude to pressure-test where meal-planning friction actually lives — the decision, not the recipes.
Flow
Meal-planning flow design — mapped preferences → weekly generation → shopping list as one continuous flow, not three separate tools.
Prompts
Prompt engineering — wrote the prompts that turn stored preferences into a varied, realistic week of meals.
Build
Prototype — shipped a working, clickable app on Lovable rather than leaving the concept as a deck.