A store like Photo Store, with your brand

I want a storefront for my business that works like Photo Store (https://photo-store-vector.superfast.shop), a demo store built on Crystallize: Every shopper sees their own store: campaigns, grids, search, the mega menu and the basket are ranked from each customer’s order history — and every position explains itself.

The content model and the wiring below are proven in that store: keep them for the features I want, and rename things to fit my trade. If a feature doesn't fit my business, leave its parts out rather than forcing it. Everything I see is mine to decide: brand, colours, typography, layout, copy and pages. Don't copy the demo's look; build my brand.

What the demo does: vector personalisation, explainable ranking, merchandising rules, typo-tolerant search, campaigns, multiple markets, multi-currency, customer price lists. It is B2C and B2B, in English; my markets and languages may differ.

How to work with me

• You need to run commands, edit files and use MCP tools. If you can't (for example in a plain chat), tell me, and suggest I paste this prompt into Claude Code, Cursor or another coding agent instead.
• Ask your questions a few at a time (three to five), in the order of the steps below, and suggest a sensible default for each so I can just say yes. Ask each thing once, even where two lists overlap, and ask the ones that change the build first. Don't start a step before the one before it is done.
• The technical detail below is for you. Talk to me in plain words, and explain a choice only when I need to make it.
• Keep the folder empty until step 5, apart from .env.local.
• Never ask me to paste an access token secret into the chat, and tell me not to paste a filled-in command or its output either. Tell me which command to run or which file to put it in, and I'll do it.
• Before you create or change anything in Crystallize, show me the plan (shapes, pieces, topics, price variants, markets) and wait for my yes. Before an import, show me a sample of five items.
• Use the Crystallize skills (the skills MCP tool, or the use-crystallize plugin) for how-to: content-model, information-architecture, taxonomy, data-creation, mass-operations, pricing, query, mutation, js-api-client, responsive-images, payments, and when this store needs them subscriptions, bookable-resources, vector-ranking and permissions. Where this prompt and a skill disagree, the skill wins. Check the live schemas with the MCP instead of guessing field names.
• When something I asked for isn't possible in Crystallize the way I pictured it, say so and offer the closest thing that is.
• The storefront never reads from the Core API on customer-facing pages. Products, public prices, stock and content come from the Discovery API and the Catalogue API; confidential prices (negotiated B2B price lists) from the Catalogue API on the server.
• Use the Shop API for everything about customers: carts, checkout, customers, orders (including orders created directly, such as renewals), order meta, pipeline stages, payments and subscription contracts. Take the customer identifier from the server session, never from the browser. The Core API is for setup scripts, back-office tools, scheduled jobs and what the Shop API can't do, always on the server and never once per page view.

Step 1: Crystallize tenant, tokens and MCP

Ask me:

1. Do I have a Crystallize account and a tenant for this store? If not, I sign up for free at https://app.crystallize.com/signup and create an empty tenant. Ask for its tenant identifier.
2. Do I have access tokens? If not, tell me: in the Crystallize App, go to Settings → Access Tokens → Generate a new token, name it, and keep the ID and the secret (the secret is shown once). A token acts with its user's role, so while we build, that user needs to be Tenant Admin (or have a role that can write shapes, pieces, topics, items and prices and run mass operations). Once the store is built, switch the MCP to a token from a read-only user.
3. Is the Crystallize MCP connected, with write access? Check that you have its write tools (run-mass-operation, mutate-core), not only the read tools (tenant-overview, fetch-content-model): with only the read tools, it was added without ?exposeWrite=true. If it's missing, have me run this in my terminal with my own token, then restart you:

   npx add-mcp "https://mcp.crystallize.com/mcp?exposeWrite=true" \
     --header "X-Crystallize-Access-Token-Id: <token id>" \
     --header "X-Crystallize-Access-Token-Secret: <token secret>"
   

   If the MCP can't be connected in my tool, say so and fall back to scripts that call the Crystallize APIs with the tokens from .env.local. In Claude Code, also suggest the Crystallize skills: /plugin marketplace add crystallizeapi/ai, then /plugin install use-crystallize@crystallize-ai. The plugin brings its own read-only Crystallize MCP entry with placeholder credentials: keep using the one added above (and add &exposeSkills=false to its URL once the plugin's skills are installed).
4. Confirm the connection with tenant-overview, and tell me what's already in the tenant. If it isn't empty, ask whether to build next to what's there or in a fresh tenant.

The storefront needs the tenant identifier and its own credentials: an access token pair for the Shop API (server only), and a static auth token if Discovery and the Catalogue API are secured. Don't reuse the admin build token in production. Put them in .env.local (have me fill in the secrets) and make sure .env* is in .gitignore.

Step 2: my business and my brand

Ask me:

• What I sell, who buys it, and what makes us different. My brand name and a one-line pitch.
• My markets, currencies and languages, and my VAT/tax setup.
• Where my product data lives today: a spreadsheet or CSV, an export from Shopify, WooCommerce or another platform, a PIM or ERP, my current website, or nothing yet. Where my product images are.
• My brand: logo (SVG if I have it), colours, typefaces, tone of voice, and two or three sites whose look I like. If I have no brand guide, propose a direction from my answers and show it before building pages.
• Where it should run: my own domain, and hosting (suggest Vercel for Next.js).

Then ask what is particular to this kind of store:

• Which brands do I carry? Which of them own a system (a lens mount, a battery or accessory platform) and which make compatible products?
• What compatibility matters in my range (camera mounts, platforms, ecosystems), and which products fit everything?
• My product types, and which ones replace each other (two cameras) and which go together (a camera and a memory card)?
• The use cases or customer interests I merchandise by (wildlife, portrait, travel, video…), and levels (beginner to pro).
• My markets, currencies and tax rates; do prices in my data include tax?
• Can I export margin, units sold in the last 30 days, ratings and stock per SKU? The ranking uses them.
• Do I have order history per customer to import (through the Shop API's /order create, never Core)? It builds each shopper's taste; without it the store starts on house ranking.
• Which campaigns am I running: name, dates, priority and which products.

Step 3: the content model

Create this in my tenant with the MCP, renamed to fit my trade, after I have approved the plan. Keep the structure: it is what the storefront's features depend on.

Build in dependency order, since mass operations run in sequence with no rollback: pieces and shapes (empty first, then their components), topic maps (at most 30 topics per topic/create), price variants, markets and VAT types, the folder tree (two to four levels, five to twelve per level), and only then items. Use lowercase-hyphen identifiers. Decide now which fields are translated and which are discoverable. Restrict every item relation with acceptedShapeIdentifiers. Never add price or stock components to a shape: variants have them built in.

• seo piece: title, description, image.
• category (folder): intro, description, hero, seo.
• brand (document): description, logo, website, seo.
• campaign (document): headline, subheading, badge, body, image (a banner with no text burned in), cta chunk (label, url), layout selection (hero, tall or square; required, so set it at creation), priority, valid-from, valid-to, products relation (max 8), seo.
• product (product):
  • description, brand relation (exactly one, set at creation), usp (repeatable chunk: text), specs (repeatable chunk: label, value), related relation → product (max 8), seo.
  • Discoverable merchandising numerics: margin (0–1), sold-30d, rating, campaign-boost.
  • One variant per product with images and stock on it. SKU as externalReference.
• Topic maps, exactly two levels, where the root is a taste dimension and the leaf its value: brand, system (mounts or platforms, plus system-agnostic), category (product types), usecase, level, price-tier. Topic order on a product matters: own brand before compatible brand, strongest use case first.
• Vector vocabularies, with weights by topic position:
  • brand: brand [1.0, 0.5, 0.25], system [1.0, 0.5].
  • usecase: usecase [1.0, 0.7, 0.45, 0.3].
  • gear: category [1.0, 0.5], level [1.0], price tier [0.8].
  • Leave out keys that mean "no preference" (system:system-agnostic, brand:other).
• Catalogue: two levels of category folders (e.g. /cameras/mirrorless-cameras, /lenses/sony-lenses, /accessories/tripods), plus /brands and /campaigns.
• Pricing: net prices (four decimals), one price variant per currency. Tax is applied per market in the cart.
• Customer groups per market and segment (B2C, B2B): B2B sees prices excluding tax by default, with a VAT toggle.
• Stock: one default location.

Step 4: my data

Import my products and content with mass operations, mapping my data onto the model: validate each file with build-mass-operation, run it with run-mass-operation and follow it with get-mass-operation-status. Read the operation logs, not just the task status: a task can finish as complete with failed operations, and there is no rollback. Give every upsert a resourceIdentifier so a re-run updates instead of duplicating, and chunk large imports. Start with a small batch, check it in the Crystallize App with me, then run the rest.

Publish every imported item in each language: the storefront only sees published versions (in a mass operation, item/publish needs real itemIds). Import images from URLs with copyRemoteAsset, or upload them (presigned upload, then registerImage). Renditions are generated in a queue: after a large import, republish once they exist, and have the storefront fall back to the original image URL while variants is empty. Before building pages, query Discovery once; if the tenant isn't ignited yet, run igniteDiscoApi (with stacks: opensearch if we use vector ranking), wait for the task to complete, and allow a few minutes. If I have no data yet, create a small, clearly labelled placeholder set (ten or so products) so we can build the pages, and remind me to replace it.

• The demo holds 350 products from about 43 brands in 28 folders, with 21 campaigns. Its merchandising signals, customers and orders are fictional.
• Build order: tenant (VAT, price variants, currency) → model (piece, shapes, topic maps, vocabularies) → images → catalogue → customers and order history → vectors (last).
• From me: products with brand, category, compatible system, use cases, level, price tier, net prices per currency, stock and images; margin, sales and rating (or proxies); campaigns; order history per customer.

Step 5: the storefront

• Next.js (App Router) on Vercel, plain fetch GraphQL clients; Crystallize's WebP renditions go straight into srcset. One catch-all route resolves category, product, campaign and brand by path.
• Discovery API (public) for all browsing: front page, campaigns, category listings with topic facets, product pages, brand pages, search, autocomplete and recommendations.
• Ranking per surface: search(context: { userTaste }, rankBy: { terms, tieBreaker }), with a badge that says why a product is where it is, built from the shopper's taste and the product's topics. Request explain: true only behind a merchandiser flag (rankExplain is null on taste-only and nearestTo-only queries).
  • Field names are per-tenant enums: introspect TenantRankByField and TenantRankByTieBreaker (e.g. fieldBoost on sold_30d_number, inStockBoost on stock_default, recency on publishedAt). A numeric you facet on can't be boosted.
  • House terms: boosts on sales (0.55), margin (0.35), rating (0.3), campaign boost (0.25), in stock (0.25), and recency (0.2, 90-day half-life).
  • Front page: tasteCosine brand 1.7, use case 1.4, gear 0.8, plus house. Category pages: 1.4 / 1.2 / 1.0 plus house. Campaigns: taste plus campaign priority. Search: relevance 2.0 plus lighter taste.
  • Upsell ("others also buy"): the basket's taste blended over the shopper's, excluding what's in the basket and products that replace it.
  • Drop the taste terms when there is no shopper taste; never send context: null.
• Similar products: nearestTo: { vocabulary: gear, like: { sku }, k } (k replaces the page size). An anchor with no gear taste returns nothing, so check before rendering; to blend in stock or margin, add a tasteCosine term from: nearestTo to a rankBy.
• Search: term with options: { fuzzy: { fuzziness: SINGLE, prefixLength: 1 } }. Autocomplete is a prefix match per word (it doesn't fix typos): use filters: { name: { autocomplete: { term } } } with the same term and sorting: { score: desc }, and drop hits with score 0. If it finds nothing, fall back to single-edit fuzzy search; use double only as a last resort.
• Shopper taste: read the customer's orders from the Shop API (orders(customerIdentifier), on the server), get each SKU's leaf topics from Discovery, and sum them, weighted by quantity (capped at 3), share of spend and recency (180-day half-life). Send one userTaste entry per vocabulary as { vocabulary, weights: { "dim:value": w }, magnitude }, where magnitude is the square root of the sum of squared weights (a wrong magnitude raises no error, so unit-test it). Read orders with limit: 100 and the identifier from the session, deduplicated by coreId.
• Shop API: a JWT from /auth/token (scopes cart, order); hydrate with taxes not included, the market's tax rate, decimals: 4 and the market's price variant; then place, and create the order with /order createFromCart once per cart (after a verified payment webhook when paying by card).
• Env: CRYSTALLIZE_TENANT_IDENTIFIER, CRYSTALLIZE_ACCESS_TOKEN_ID, CRYSTALLIZE_ACCESS_TOKEN_SECRET.

Build my design, not a demo's: my typefaces, colours and tone, with pages that suit my products. Show me the home page, a category and a product page early, and adjust the design with me before building the rest.

Every page is built for search engines, answer engines and AI agents from the start, not added at the end:

• SEO: server-rendered HTML, one <h1>, a unique title and description, canonical URLs, hreflang per language, a sitemap and robots.txt, and clean, translated paths.
• Structured data: JSON-LD on every page that has a subject: Organization and WebSite (with a SearchAction) on the home page, Product with Offer (price, currency, availability) on product pages, BreadcrumbList on categories and products, Article or Recipe on content. Generate it from the same data as the page.
• GEO, for answer engines and agents: /llms.txt (an H1, a summary, links to every section), /llms-full.txt, and a Markdown twin of every page (its URL plus .md, or Accept: text/markdown), with prices, stock and facts written out in plain sentences.
• Agents can act, not only read: register the store's actions (search, add to cart, check availability) with WebMCP (navigator.modelContext.registerTool, or annotated forms), and keep the accessibility tree clean: semantic HTML, labelled controls, real buttons and links.
• Fast and stable: responsive images from Crystallize, no layout shift (reserve space for images and late content), little client JavaScript. Aim for 100 in every Lighthouse category (Performance, Accessibility, Best Practices, SEO; heavy 3D or video pages may score lower on performance) and pass every Agentic Browsing check.

Step 6: run it, then ship it

Run it locally and walk me through each feature above with my own data. Fix what I find. Before you call it done, run Lighthouse on the home page, a category and a product page (npx lighthouse <url> --only-categories=performance,accessibility,best-practices,seo,agentic-browsing), validate the JSON-LD (https://validator.schema.org), open /llms.txt and a page's .md twin, and fix what falls short. Deploy only when I ask: set the same environment variables on the host, point my domain, and give me the live URL.

Watch out for

• Vector ranking must be enabled for the tenant, then indexed with igniteDiscoApi(stacks: opensearch): poll the task until complete and allow a few minutes. Detect the capability by checking that __type(name: "RankByInput") is non-null, not by error text; ExperimentalFeaturesNotAvailableError means ranking isn't enabled.
• Vectors go last, in this order: vocabulary (upsertVocabulary replaces it whole) → setItemTaste (it writes the draft and empties variant components) → rewrite variant components → publishItem per item and language → igniteDiscoApi(stacks: opensearch). After the first index, pass the vocabulary as an unquoted enum.
• Topic maps must be exactly two levels for the path-to-taste-key rule (or store the taste key in each topic's meta); share the taxonomy code between the setup scripts and the storefront.
• Pass required components (the brand relation, the layout selection) when creating items, not afterwards.
• Create shapes empty first, then add their components, so relations and pieces resolve.
• Changing a price later needs modifyProductVariantPrice and a republish.
• Keep four-decimal net prices and decimals: 4 in the Shop API, or basket totals are off by pennies.
• Under rankBy, term still decides which items match; only a relevance term makes the text match affect the order. Don't pass sorting with ranking; page ranked lists with skip and limit inside the rerank window (500 by default). Double fuzziness on full search matches nearly everything.
• Discovery rejects explicit null variables: leave them out.
• Don't invent facts about my business (prices, stock, certifications, delivery promises). Ask, or leave a clearly marked placeholder.

And for every Crystallize store, from the skills:

• Orders: create and change them through the Shop API /order (createFromCart, create, setMeta with merge: true, addToStage, setPayments). Editing an order in Core adds a duplicate to the Shop API's list. Read a customer's orders with the identifier from the session, limit: 100, grouped by coreId (keep the newest). Seed order history through /order create, not Core registerOrder. The order id is the cart id; don't call fulfill after createFromCart.
• Payments: create the order from the payment provider's verified webhook, never from the browser, once per cart.
• Cart meta goes in hydrate(input: { meta }); hydrate is the whole cart, so send every line each time.
• Images: serve them straight from Crystallize (not through an image optimizer such as next/image in its default setup): a WebP srcset from the returned variants with an accurate sizes, falling back to the original URL while renditions are missing. Replace an image by uploading a new one, not with registerImageRevision.
• Ranking (if the store ranks per shopper): check that __type(name: "RankByInput") exists; pass context as a variable, with userTaste entries of { vocabulary, weights, magnitude } (magnitude = the square root of the sum of squared weights); tieBreaker is required; don't combine sorting with ranking, and page with skip and limit inside the rerank window; introspect TenantRankByField for field names; leave context out when there's no taste; use explain: true only for tuning.
• Bookings (if the store books): durations are in seconds; the role needs the bookingPolicies permission; put the customer on the cart before bookSkuItem; every hydrate must resend each booked line with its window and unit, or the booking is cancelled; remove a booking by re-hydrating without it.

Done when

• My tenant has the content model above with my products, prices and images in it.
• The storefront runs on my domain in my brand, and every feature I chose works with my data: we have clicked through each one together.
• Lighthouse scores close to 100 in every category and every Agentic Browsing check passes on the home, category and product pages.
• I know how to add a product, change a price and publish, in the Crystallize App.