Foodai
AI-powered nutrition app · UX/UI redesign focused on generative meal planning, clear onboarding, and a scalable component system.
CLIENT
InfinityAppCraft (IAC)
ROLE
Freelance UX/UI Designer
DURATION
Sep 2024 – Jul 2025
TOOLS & METHODS
User Research
UX/UI Design
Product Development
Product Strategy
Prototyping
Design System
Figma
Lottie
Adobe Photoshop
Hotjar
PROJECT CONTEXT & VISION
Foodai is an AI-powered app for personalised recipes. When the project started, there was a functional prototype (MVP), but it lacked clear user guidance, visual language and structural depth. The goal was to holistically optimize and redesign the app's UX and UI.
The central question, ‘What should I cook today?’ is one we all ask ourselves often, and it means we have to start searching for inspiration all over again.
Foodai is aimed at young adults (aged 18-35) who want to eat healthier and cook for themselves, but have little time for planning and research. Whether singles, couples or families, the app uses AI-generated recipes, weekly plans, shopping lists and intelligent filters to help establish routines and make cooking easier, healthier and more personalised every day.
OBJECTIVES
Validate the assumed user group and derive new features if necessary.
Improve prototype (MVP) through heuristic UX evaluation and research findings.
Redesign the structure and visual design of the app.
Define and prioritise existing and new features for the product roadmap.
RESEARCH OBJECTIVES
The aim was to review assumptions about the target group (18–35 years old) and gain a better understanding of their behaviour when it comes to cooking, planning and shopping. The focus was on three questions:
Challenges & frustrations – What are the everyday problems when it comes to planning, shopping, cooking and finding recipes?
Relevance of the assumed target group – Are they actually suitable as the primary user group for FoodieAi?
Use of existing tools – Which digital aids are currently being used, what is missing, and how is an AI-supported recipe app perceived?
ONLINE SURVEY ON TARGET GROUP VALIDATION & EVERYDAY REALITY
To validate the target group, an online survey was conducted with 14 deliberately diverse individuals (aged 20–39).
It combined quantitative questions about cooking and planning behaviour with open-ended questions about personal challenges, needs and attitudes towards recipe tools.
The insights gained were then structured, converted into thematic areas and recurring statements, and used as a basis for persona development and feature prioritisation.
USER FLOW & FEATURE PRIORITISATION
The survey findings along with the heuristic evalutaion of the prototype led to an optimized user flow with clearer, more intuitive navigation and an optimised structure. Existing functions were reorganised and expanded to include key features, including:
Daily & weekly planner
Automatic shopping lists
Extensive filter options for different user needs
New navigation structure (tab bar + header):
Generate – central button for recipe generation
Discover – personalised recipe suggestions & inspiration
Recipes – overview of all generated & saved dishes
Planner – create weekly & daily plans
Shopping – automatically generated shopping lists
Top right of the app – token display (credit) & settings (profile-filter, co-profiles, language, units, darkmode etc.).
DESIGN SYSTEM
The visual design connects technological intelligence (AI), chat interface patterns, and healthy nutrition.
Fresh nutrition-related colours (green, orange, white, black) meet a clear, modular UI.
Typography, colour, iconography and layout are based on familiar chat and messenger patterns, supported by emojis, making interaction with AI accessible and intuitive.
Beyond colours, typography and layout, a component-based system was developed with clear semantic roles for each design token. This makes developer handoff more efficient and ensures visual consistency.
The design follows Apple’s Human Interface Guidelines (HIG) in terms of navigation structure, interactive areas, button sizes and accessibility, and focuses on consistent spacing and high visual scannability.
