# Habitly

> A Greek-language AI nutrition and habit coaching product: a personalised meal plan with macros, photo-based food logging and an assistant, built so the model never owns the numbers.

- Canonical HTML: https://www.digiminds.gr/en/work/habitly
- Markdown representation: https://www.digiminds.gr/ai/en/work/habitly.md
- Language: en-US
- Alternate language HTML: https://www.digiminds.gr/work/habitly
- Alternate language Markdown: https://www.digiminds.gr/ai/el/work/habitly.md
- Project year: 2026


## Overview

The AI writes the meal plan. It never owns the numbers — those come from a compiled catalogue, because a wrong macro is a health claim, not a typo.

## The problem

A nutrition and habit product for the Greek market: an onboarding questionnaire turns into a personalised plan with macros, meals and daily habits, with photo-based food logging and an assistant for day-to-day questions.

## Goal

Make a personal plan feel generated for you, while keeping every number and safety rule out of the model's hands.

## Role

Freelance engagement: built the product and its agent architecture.

## The challenges

- Nutrition figures carry real consequences, so anything a language model produces has to be treated as a draft rather than a fact.
- A plan that fails validation is worse than useless if the fix is to generate a new one — the user loses what they already agreed to.
- Photo-based food logging arrives as whatever the phone produces, including formats a browser will not decode on its own.
- Several specialists contribute to one plan, so context has to be scoped per stage or the whole history leaks into every call.
- Subscriptions, privacy requests and model costs all need to be auditable, which rules out doing them in the client.

## The solution

- Nine AI specialists behind one product — intake, macros, meal planning, plan finalising, a health advisor, a photo-based food recogniser, a progress tracker and a chat companion — each with a strict input and output schema.
- A hard boundary between the model and the truth: AI drafts blueprints and recipes, while the numbers and safety rules come from a deterministic catalogue compiled from a source ledger.
- Shared memory derived only from real events in the app; assistant output is never treated as evidence about the user.
- Validators that check without mutating, and a repair step that runs before anything is regenerated — so a bad plan is corrected rather than rerolled.
- Subscriptions, admin operations, privacy requests and model-usage accounting all run as server-side functions rather than in the client.

## Facts

- **team:** Freelance engagement
- **status:** In development

## Technology

- React
- Vite
- TypeScript
- Supabase
- Stripe
- TanStack Query
- Tailwind CSS
- Radix UI
- Zod

## Source notes

This Markdown representation is generated from the same project data used by the DigiMinds case-study page. It does not add performance metrics, client claims, or outcomes that are not present in the project source.