The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Food as Healing AI is a personal AI nutrition and food intelligence platform designed around the individual.
The platform builds a persistent Personal Nutrition Profile from the user's goals, food habits, lifestyle, preferences, restrictions, ingredient policies, practical constraints, feedback, and optional user-provided laboratory context.
Its food intelligence pipeline uses Vision/OCR, ingredient extraction and normalization, an ingredient and additive knowledge base, RAG, and structured product analysis to help users understand what is actually represented in a food product.
A Personal Matching Engine is designed to connect structured product information with each user's individual food policy — including hard exclusions, preferences, dietary patterns, nutrition goals, clean-label requirements, and ingredient rules.
The broader architecture is modular and multi-agent. Specialized agents are designed for personal profiles, questionnaires, nutrition, ingredients, products, matching, shopping, meal planning, knowledge retrieval, and continuous feedback.
The current technical foundation includes a Google Cloud backend, Supabase, RAG, prompt/AI orchestration, external AI model integration, an ingredient/additive knowledge base, and an image-based ingredient analysis prototype.
The goal is not to provide another generic diet app or diagnostic system, but to create a personal AI food consultant that learns how an individual wants to eat and turns that profile into explainable everyday food decisions.
The multi-agent split (profiles, matching, meal planning, feedback as separate agents) makes sense given how different those tasks are, but that's a lot of moving pieces to keep consistent. Curious how you're using Supabase alongside Google Cloud here — is it mainly the...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
The Last Memory
Coin cabinet — Charles Percier, Paris, ca. 1809–19
The Last Memory reimagines Charles Percier's Coin cabinet as an archive of human memory. Instead of preserving coins and medals, its drawers preserve fleeting fragments of human life. Most compartments have gone dark, leaving only a few fragile memories behind. I kept the cabinet grounded in the visual language of a real museum artifact and introduced one impossible idea: what if memory itself could be physically preserved?
Thanks for your submission! If you claim the free credits through the process outlined in the submission guidelines, your image will not contain the Flora watermark. You can then re-upload your submission, with a clean version your image!
When designing a music app, most teams start with the player screen.
We did too. It's the obvious center of gravity.
But when we worked on this concept, we noticed something. The player was the least interesting design challenge. Every music app has a player. Not every music app knows what you actually listen to.
So we built around the intelligence layer first Sound Intelligence. 18h 42m of listening time. 239 songs played. Peak listening 9 PM–12 AM. Genre distribution mapped across Lo-fi, Pop, R&B, and Others in a horizontal bar system that makes your taste visible at a glance.
The player came second. The library came third. And the AI Discovery panel 24 tracks, 96% match came last, because by the time a user reaches it, the app has already proven it understands them.
What we noticed was that designing analytics before aesthetics made the whole product feel smarter. The visuals followed the data, not the other way around.
Does your music app know you as well as this one does?
Love how intuitive this mobile app design is
If you saw our previous Filanov Care post, here’s a closer look
This time, we’re diving into the AI healthcare intelligence platform we designed at JetDesigns.
We brought together AI-powered insights, patient context, and clinical workflows into one focused experience — making complex healthcare information easier to navigate and act on.
Less searching. More understanding. Better decisions!
#HealthTech #AI #SaaS #ProductDesign #UXDesign #UIUX #HealthcareInnovation
