Work / Mobile AI / Live

Meal photo nutrition tracking app

A Flutter app that estimates the foods and portions in a meal photo, lets the user confirm them, and logs nutrition in seconds.

Problem

People give up on food tracking because searching a database and typing every item takes too long.

Objective

Make logging a meal as quick as taking a photo, while keeping the user in control of the final entry.

Solution

  1. 01

    The app compresses the photo on device and sends it to a vision model that returns likely foods and portion estimates.

  2. 02

    Estimates are matched to a nutrition database, and the user confirms or adjusts each item before saving.

  3. 03

    Frequent meals are remembered, so repeat logging takes one tap.

  4. 04

    The app gives general tracking information only, not medical or dietary advice.

Architecture

01
Flutter app
02
On-device compression
03
Vision model
04
Nutrition database
05
User confirmation
06
Backend + sync

AI workflow

01

Take a photo of the meal

02

Detect foods and estimate portions

03

Match items to nutrition data

04

User confirms or edits

05

Log and sync the entry

Technology & role

Flutter / DartRiverpodGemini APIFirebaseNutrition API
Our role

Product design, Flutter development, AI integration and backend.

Start here

Want something similar built?

Send a short brief. We'll reply personally with questions or a suggested next step — usually a technical discovery call.