Ladle

Rescue your neighborhood's surplus food and pay a meal forward - a hyperlocal map where leftovers find a hungry neighbor in minutes, not a landfill.

Ladle is a hyperlocal food-rescue marketplace that turns the surplus food sitting in your kitchen - the half-tray of lasagna, the bagels you over-bought, the garden tomatoes you'll never finish - into a meal for a neighbor, before it spoils.

Instead of scrolling endless listings, you point your phone at the food and Ladle's on-device camera recognizes what it is and drafts the listing for you. It drops onto a live neighborhood map with a freshness countdown, and anyone nearby can claim it for free or for a few dollars. With one tap you can also "pay it forward" - funding a suspended plate that someone facing food insecurity can claim anonymously, with dignity.

The result is a faster, warmer way to move food from people who have too much to people who have too little - block by block, in real time.

The Problem

The United States throws away 30–40% of its food while tens of millions of people go hungry. The two problems sit side by side, unconnected.

Existing apps mostly rescue business surplus (cafés, bakeries, grocers). The everyday surplus in millions of home kitchens - and the neighbor two doors down who could use a meal - is almost entirely unserved, because listing food is tedious and there's no dignified way to give directly to a person in need.

Ladle explores a different question:

What if surplus food could move peer-to-peer, in real time, as easily as taking a photo - and what if giving a meal felt as good as getting one?

By combining on-device food recognition, a live hyperlocal map, and a pay-it-forward "suspended plate" mechanic, Ladle removes the friction that kills food-sharing and channels the urgency of "use it before it spoils" into a pro-social act.

Links

Live Project: https://ladle-84447.bubbleapps.io

Category

Marketplace - a peer-to-peer platform for giving, claiming, and paying forward surplus food.

Process

Ladle combines AI-assisted no-code development, on-device computer vision, and real-time geolocation, built on Bubble.io and Claude.

Development Workflow

The entire foundation was generated from a single Bubble AI prompt - pages, database schema, workflows, authentication, and seed data - then refined by hand. I used Bubble AI to scaffold the marketplace, then took the wheel: embedding the camera food-detection model, and designing the suspended-plate flow and the community impact dashboard.

Food Detection (on-device camera)

When a giver adds a photo of their surplus food, Ladle runs an image classifier entirely in the browser — no server, no API key, no quota — and auto-fills the listing with the detected food.

It uses TensorFlow.js with the MobileNet model (1,000 ImageNet classes, many of them foods — bagel, French loaf, pretzel, pizza, banana, lemon, and more), loaded in Bubble's native HTML element and bridged back into the app with the Toolbox plugin (Run JavaScript + JavaScript-to-Bubble). The detected label pre-fills the food name, and the giver can edit it before posting — turning a tedious listing into a single tap. (COCO-SSD is also supported for object-style detection of common foods like pizza, banana, and donut.)

APIs & Integrations

TensorFlow.js — MobileNet / COCO-SSD — on-device food image recognition, no API key — github.com/tensorflow/tfjs-models

Plugin — Toolbox (Mishav) bridges the in-browser CV model to Bubble.

Research & Problem Validation

Ladle's problem is real, measured, and unsolved in the peer-reviewed literature:

Conrad, Z. (2020). Daily cost of consumer food wasted, inedible, and consumed in the United States, 2001–2016. Nutrition Journal, 19(1):35. — Across 39,758 adults (NHANES), about 27% of daily per-capita food spending goes to food that is ultimately wasted (~$1,300/year per household), pointing to the consumer level as the highest-leverage place to intervene. https://doi.org/10.1186/s12937-020-00552-w nih

von Massow, M., et al. (2019). Valuing the Multiple Impacts of Household Food Waste. Frontiers in Nutrition, 6:143. — A detailed household audit quantifying the economic, nutritional, and environmental cost of avoidable household food waste. https://doi.org/10.3389/fnut.2019.00143

Principato, L., Mattia, G., Di Leo, A., & Pratesi, C. A. (2021). The household wasteful behaviour framework: A systematic review of consumer food waste. Industrial Marketing Management, 93, 641–649. — A systematic review confirming that roughly one-third of the food produced globally is lost or wasted along the supply chain, with household waste driven mainly by everyday food-related behavior. https://www.sciencedirect.com/science/article/abs/pii/S0019850119308600 ScienceDirect

Dunn, E. W., Aknin, L. B., & Norton, M. I. (2008). Spending Money on Others Promotes Happiness. Science, 319(5870), 1687–1688. — The behavioral engine behind the suspended-plate feature: spending money on others promotes greater happiness than spending it on oneself. https://doi.org/10.1126/science.1150952 Science

Context: USDA estimates U.S. food loss and waste in the hundreds of billions of dollars annually, while ~47 million people lived in food-insecure households in 2023 (USDA ERS) — the exact gap Ladle is built to close.

Sources & Imagery

Demo food photography is sourced from Unsplash (a unique image per listing). Nutrition data is provided by Open Food Facts.

Tech Stack

Bubble.io · Bubble AI · Claude · TensorFlow.js · MobileNet / COCO-SSD · Toolbox plugin · Mapbox · OpenStreetMap Nominatim · Open Food Facts · Unsplash