unthinkable
Case study · A healthcare company, France · personalised meal planning

Users get a diet plan built around their health, their allergies and the food sold where they live.

The company wanted people to get nutrition plans that fit their health needs and use the foods they can actually buy locally, so they can stick to them.

FranceCorporate & consumer wellness

What changed

50%more active users in the first three months (as reported)
15+diet types supported (as reported)
50+countries covered with local meal suggestions (as reported)
What stood in the way

What stood in the way.

What stood in the way
  • People struggled to find diet plans that fit their health needs and used local foods, got frustrated and dropped the diets.
  • A useful plan had to weigh goals, activity, medical conditions, allergies and past health history together.
What changed
  • 50%more active users in the first three months (as reported)
  • 15+diet types supported (as reported)
  • 50+countries covered with local meal suggestions (as reported)
What we built

What we built.

  • A discovery workshop with user stories and personas to set the platform's features.
  • A React front end, a Node.js and Express backend and MongoDB for health records and preferences.
  • GPT-4o mini in the backend, generating each plan from the user's location, goals, health details and dietary restrictions.
  • A profile using gender, age, height and weight to work out calorie and nutrient needs, plus location for local ingredients.
  • Recipe search, dietary preferences such as vegan or gluten-free, goals and activity, and allergies and history so plans avoid harmful foods.
  • React.js
  • Node.js
  • Express
  • MongoDB
  • GPT-4o mini
What it shows

What this work shows about us.

A plan people keep

Users singled out meals built from locally available food as what helped them stick with the plan (as reported).

Health details first

Allergies, conditions and history shape every plan, so the advice fits the person, not an average.

Want to build a similar diet planning platform? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.

Start your plan ↗
If we built it today

If we built it today, with AI.

What we would add now, moment by moment.

Seeing the doctor

An agent would summarise a user's logged progress, conditions and plan changes for their doctor or dietitian before a visit, who decides any medical change.

Going home

An agent would check in each week on weight and energy, adjust meals within the safe limits set for the user's conditions, and pass anything unusual to a person.

Ask Unthinkable

Want this for your business?

Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.

Send us a note instead

Required

Thanks. A senior AI engineer will reply to you.
u
Ask UnthinkableClarity first, then the right team
Your conversation

An AI agent. This prototype uses prepared answers and sends nothing.