Case study
AI Nutritionist & Automated Meal Planning
- Client: gbMeals
- Industry: Health & Fitness
- AI capability: Generative AI
The challenge
Meal plans have to be personal, realistic and safe, every week
Generating accurate, tailored meal plans at scale is complex. The system needed to ingest user preferences from an intake form and output modern, personalized PDFs containing everyday-cooking recipes and dedicated bulk meal-prep plans. A critical challenge was ensuring the specialized LLM did not hallucinate ingredient quantities or suggest meals that violated user dietary restrictions.
What we built
Structured intake, guarded generation, automatic PDFs
Constraints are enforced around the model, not left to it.
- Stage 1
Normalise the intake form
Goals, body metrics, dietary restrictions, cooking habits and ingredient preferences are captured in a detailed intake form, then normalised into a structured schema of calorie targets, macro ranges and excluded ingredients.Structured preference record - Stage 2
Generate the week's plan
A specialised meal-planning model writes the week: everyday recipes plus an optional bulk meal-prep plan for people who cook once for the week, with ingredient lists and preparation steps for a home kitchen.Recipes and prep steps - Stage 3
Check it against the constraints
Validation layers test every output against the user's dietary restrictions, ingredient safety rules and realistic quantity ranges. Anything inconsistent is corrected or regenerated before it is seen.Plan that respects restrictions - Stage 4
Build the PDF and send it
Recipes, instructions and a consolidated shopping list are formatted into a clean PDF, then emailed to the user on a recurring schedule.Personalised PDF, delivered by emailAutomated PDF generationScheduled email
The impact
Personalised nutrition that scales
- A weekly plan and shopping list per user
- Dietary restrictions enforced by validation
- Delivered by email on a schedule
gbMeals can now instantly provide users with quick, simple recipes anyone can follow, alongside an organized shopping list with every plan. This automation scales their personalized nutrition service while maintaining high quality and strict dietary safety.
Project showcase
More from the project
Keep exploring
Related case studies
Real Estate & PropTechGenerative AIAI-Powered Virtual Staging and Renovation
Buyers respond better to furnished rooms, but physical staging is expensive and slow. PropTech founders and real estate agency owners need a highly scalable, photorealistic virtual staging automation tool that works instantly.
- Lower staging cost than physical staging
- 90%+
- Increase in inbound leads on staged listings
- 40%
Health & FitnessGenerative AIPharmaBrain: Private, Air-Gapped LLM for Medical Research
Atacana needed a private, air-gapped LLM deployment: a medical research assistant that answers complex questions over thousands of proprietary news reports and drug discovery updates each day, without any data leaving its own servers.
- Offline, on local servers
- 100%
- Quantized Mixtral 8x7B
- 8-bit
Health & FitnessGenerative AI & Recommender EnginesHā Health: Comprehensive AI Wellness Ecosystem
Hā Health wanted to offer users a comprehensive, AI-driven health and wellness experience, combining personalized meal, exercise, and meditation recommendations with dynamic recipe creation and automated meal planning. We delivered a cross-platform solution with AI-powered modules accessible via website, Android, and iOS apps.
Multi-platform AI ecosystem. Agentic recipe creation. Automated grocery integration.
Read the case study
Book a strategy session
Talk to an AI engineer about your project
Tell us what you want to automate. The first call is a 30-minute working session with an engineer, not a sales pitch.
- Send the form, it takes 2 minutes
- We reply within 1 business day, under NDA if you need it
- A 30-minute call to scope feasibility and next steps