A fresh Shopify experience built for Lula Oil 🥑

Creating a clean, modern e-commerce experience that puts the product and brand story at the center.

From the visual direction and product presentation to the responsive Shopify experience, every detail was designed to make the brand feel premium, natural, and easy to explore.

✨ Clean & modern UI 🥑 Product-focused experience 🛍️ Shopify e-commerce development 📱 Responsive across devices 🌿 Natural, premium brand aesthetic

Here’s a look at some of the visuals and videos from the project.

Built with Shopify.

Nice translation of the avocado-oil branding into the PDP. Since this is a consumable people reorder on a cycle, is there a subscribe-and-save or reorder-reminder flow built in, or is the launch scope first-purchase-only for now? That's usually where the real revenue sits on a...

AI Assistant Using Your Business Knowledge Base — RAG on Your Documents

THE PROBLEM Q&A bots break down when knowledge lives in documents: a 100-page manual has no "questions" to match, it can't fit into a prompt, and generic chatbots hallucinate instead of admitting what they don't know.

THE SOLUTION A RAG (Retrieval-Augmented Generation) knowledge base: documents are split into meaningful chunks, embedded into a vector index, and the assistant answers from the right sections — by meaning, not keywords.

Any format as-is: PDF, DOCX, TXT, Markdown — 100+ pages is fine

Answers grounded in YOUR documents — it says "I don't have that information" rather than inventing

Source references — every answer shows which document and section it came from

Runs on your infrastructure — documents never leave your control

One command to re-index after updating documents — documented, no programmer needed

LIVE DEMO Ask it about my products, pricing, deployment and support — it answers from 6 real documents with sources: https://kb-assistant-demo.dvc-ai.workers.dev

The 'I don't have that information' line is the part most RAG builds skip, and it's the one that matters. How do you set the cutoff? On mine, a fixed similarity threshold broke once I filtered results by user role. Scores shifted and it refused questions it could answer.