Product-family discovery and editorial buying-guidance patterns
One connected build
From shop data to a live business experience.
AI works through Selldone MCP, turns approved business data into the experience, then prepares a reviewable launch.
- 01 Connect the shop Scoped Selldone MCP access
- 02 Shape real data Catalogue, products, pricing, and operations
- 03 Build the experience AI creates every responsive surface
- 04 Review and launch GitHub to Cloudflare, with approval
See the complete build logAll 4 verified steps and outcomes
-
01
Connect the intended shop
Use an approved Selldone MCP connection for the shop that should receive the storefront. Keep the existing products, categories, prices, stock, and settings as the source of truth.
A clear, authorized scope for the storefront work. -
02
Audit real product data
Review product families, model names, variants, media, technical specifications, prices, and availability before changing the interface or filling any gaps.
A factual product brief grounded in the connected shop. -
03
Adapt the visual pattern
Apply the product-led hierarchy to the audited catalogue while replacing the reference content, assets, copy, and brand treatment with approved materials.
A business-specific interface without copied protected identity. -
04
Review before launch
Check the storefront at responsive widths, verify product data and flows, then prepare a repository, Cloudflare build, and domain only when their owners approve them.
A reviewable path from local build to authorized launch.