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
She3rris Boil — AI-Powered Food Commerce Experience
She3rris Boil is more than a restaurant website. I designed and developed a complete digital experience for a seafood-boil brand, combining e-commerce, AI, storytelling, customization, loyalty, and catering into one customer journey.
The Concept
The goal was to create a digital home for She3rris Boil that feels as energetic and memorable as the food itself — while making it incredibly simple for customers to discover, customize, and order their boil.
What I Built
AI-powered “Find Your Boil” — helps customers discover a boil based on their preferences, group size, spice level, and experience.
The Sherris B3 AI Guide — an intelligent assistant that helps customers navigate the menu, drops, pickup information, catering, and common questions.
Build Your Own Boil — customers can customize their seafood, sides, and spice level.
Online ordering experience — designed around She3rris Boil’s weekly drop model.
Loyalty experience — a digital stamp system designed to encourage repeat purchases.
Catering experience — dedicated flows for birthdays, corporate events, private parties, festivals, and larger orders.
Brand storytelling — communicating the culture, energy, and heritage behind the seafood-boil concept.
Mobile-first UX — designed to make discovering and ordering food effortless on mobile.
SEO / AEO optimization — structured the content to improve discoverability across traditional search and AI-powered search experiences.
The Bigger Idea
Instead of treating the project as a traditional restaurant website, I approached it as a digital food-commerce platform.
The experience connects:
Discovery → AI Recommendation → Menu → Customization → Ordering → Loyalty → Catering
The result is a digital ecosystem designed not only to present the brand, but to actively help customers make decisions and convert into customers.
My Focus
Product Design · UX/UI · AI Integration · E-commerce · Brand Experience · SEO/AEO · Conversion · Mobile Experience
Live project: sherrisboil.life
sherrisboil.life
She3rris Boil · Seafood Boil Stockholm & Sverige
Sveriges första seafood boil. Beställ online, välj upphämtning fre–sön och betala i kassan. Seafood buckets med hemlig signatursås i Stockholm.
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
Related posts
✨Two creative directions. One product.
Which AI-generated visual do you love more Version 1 or Version 2?
Your opinion matters! Let me know your favorite in the comments👇🏻
2 voted
40%
3 voted
60%
5 votes
Closed
Version 1 is really stunning great job Mary 🎉🎉🔥🔥
CRAG — Self-Correcting Research Assistant
Overview
A research-assistant project exploring how AI applications can retrieve information and improve the quality of their responses through a self-correction workflow.
Project focus
Python-based AI application development.
Retrieval and research workflow design.
Improving answer reliability through evaluation and correction.
Technologies: Python, AI, retrieval-augmented generation.
Self-correcting retrieval is the upgrade RAG has needed, Daniel. Most systems stop at the first retrieval and hope for the best, so building evaluation and correction into the workflow is a real reliability win. The live telemetry dashboard makes it feel production-ready.
My AI assistant runs all day. The expensive model only does the thinking.
Most requests need no AI at all. "Call me in 30 minutes" is handled by plain code. Reminders, schedules and limits are code too.
Short tasks like sorting and scoring go to fast models on a free tier.
The big model only gets planning and long conversations, where it actually has to think.
If it hits a limit, a backup model answers instead of the app going silent.
If your AI app's bill keeps growing, check what really needs the big model.
What does your app send to the most expensive model?
Same pattern holds in outbound tooling. Filtering, dedupe and enrichment lookups are plain code. The model only writes the first line once the row is already verified. Cuts cost and the weird outputs.