# Build my own food wholesale store on Crystallize, like Food Universe

I want a storefront for my business that works like **Food Universe** (https://food-universe.superfast.shop), a demo store built on Crystallize: A food wholesaler built live in an hour: case prices, GS1 data and allergens, recipes that sell their ingredients, and trade customers ordering on invoice within their credit limit.

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: invoice and credit limits, shoppable content, gs1 and allergens, volume tiers. It is B2B, in English, Dutch, Norwegian; 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:
   ```bash
   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 product feed or export do I have: GTIN, pack sizes, ingredients, allergens, nutrition, storage temperatures? Do I have packshots? (GS1 fields are ideal; Open Food Facts is a free fallback for branded retail products.)
- What do I sell by: the case or the unit? Which currencies and VAT rates (food is often a reduced rate)? Do my prices include VAT?
- Do I sell B2B, B2C or both? Do my trade customers have credit limits, payment terms and their own contract prices?
- My category tree, and what buyers filter on: brand, cuisine, diet, allergens, storage.
- Do I have recipes or other content that should sell the products in them?
- Do I need stock or delivery slots (chilled and frozen logistics)?
- How do customers pay: invoice only, or card too (and through which provider)?

## 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.

Every component is discoverable. Item relations are not translated.

- Pieces:
  - `seo`: title, description, image.
  - `nutrition` per 100 g, all numeric: energy (kJ and kcal), fat, saturated fat, carbohydrates, sugars, protein, salt.
- **category** (folder): description, hero, seo. **folder** (folder): description, seo.
- **brand** (document): logo, tagline, description, website, featured products (max 8), seo.
- **allergen** (document): GS1 allergen code, icon, description, `eu-regulated` boolean. The EU 14, split into their sub-types, as items.
- **product** (product):
  - `brand` relation (exactly one), tagline, description, ingredients (rich text).
  - `segments` selection (foodservice, retail), `diet-types` selection (vegan, vegetarian, gluten-free, lactose-free, organic).
  - `identifiers` chunk: GTIN (13 digits, validated by pattern), supplier number.
  - `allergens`: repeatable chunk of an allergen relation and a level (contains or may contain).
  - `nutrition` piece; `storage` chunk (ambient, chilled or frozen; min and max °C).
  - `commercial` chunk for ranking: margin %, sales velocity (cases a week), return rate %.
  - `recipes` relation → recipe (back-links, max 12), `related-products` (max 8), seo.
  - One variant per product, the case, with flat variant components (content chunks on variants may not publish): `units-per-case` and `unit-net-content` (numeric) and `pack-label` (single line, e.g. "6 × 450 g").
- **recipe** (document): image, intro, servings, prep and cook time, difficulty, diet types, `ingredients` (repeatable chunk, translated: quantity, unit, name, and a relation to the product that sells it), steps (paragraphs), tips, related recipes, seo.
- Topic maps: `cuisine` (two levels, e.g. asian → thai), `occasion`, `product-type` (group → type, e.g. sauces → soy sauce), `main-ingredient`, and `asset-type` for tagging images (packshot, recipe photo, brand logo).
- Catalogue: root folders `/products` (flat category folders underneath, products directly in them), `/brands`, `/recipes`, `/allergens`. Paths are translated from the item names.
- Pricing: one price variant, excluding VAT, per case. VAT applied in the cart.
- Contract pricing: price lists targeted at one company each (`targetAudience: { type: SOME, customerIdentifiers: [company] }`; its contacts inherit it), on all SKUs or some. Prefer percentage modifiers: they keep volume tiers, while an absolute list sets a flat price.

## 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 `itemId`s). 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's 435 products come from an anonymised supplier export with GS1-style fields and packshots. Prices, GTINs and ranking signals were generated. Recipe photos were made with an image model from one shared style prompt.
- The AI translated and classified the products (topics, diets, segments) in batches, then validated them.
- Build order: model → topics (with translations) → images (tagged by asset type) → folders, brands, allergens → products → recipes and back-links → publish per item and language → customers → order history (Shop API `/order` `create`, never Core `registerOrder`) → taste, publish, re-index.
- From me: a product feed, packshots and logos, prices, customers and their terms, and recipes. Missing recipes can be written and illustrated with me, clearly marked.

## Step 5: the storefront

- Next.js (App Router) on Vercel, plain `fetch` GraphQL clients, one catch-all route that resolves the item at each path. URLs are `/<lang>/<path>`.
- **Discovery API** for every catalogue read:
  - Category pages: browse products under the category path, with disjunctive facets (one query per facet, leaving that facet's own filter out) over brand, topics and diet types. Without a taste: sort by sales velocity, then item id. With a taste: `rankBy` only (sales velocity as a `fieldBoost`), no `sorting`, paged with `skip` and `limit`.
  - Search: `search(term)` ranks by relevance. Suggestions: `filters: { name: { autocomplete: { term } } }` plus the same `term` and `sorting: { score: desc }`, dropping hits with score 0.
  - Path resolution: `search(path: "<path>", pathResolutionMethod: canonical)` returns the item and its shape at a path.
  - Drafts for preview: token headers plus `publicationState: draft`.
- **Shop API:** the server exchanges the token for a JWT (`/auth/token`, scopes `cart`, `cart:admin`, `order`) and caches it. `hydrate` with the full item list every time and `decimals: 4`; the cart id lives in an httpOnly cookie. Order history from `/order` `orders(customerIdentifier, limit: 100)`, the identifier from the session, deduplicated by `coreId`.
- **Checkout on invoice:**
  1. Check credit: the limit minus the gross total of unpaid orders. Load the company's credit limit and terms once at sign-in on the server and keep them in the session, never per page view.
  2. `hydrate` with the company as customer, and meta for who ordered and the PO reference.
  3. `place`, then `/order` `createFromCart` with `paymentStatus: unpaid` and `payments: [{ provider: "invoice", method: "invoice", amount }]`.
- **Trade customers (created in setup through the Core API):** each company is an organization customer with credit limit, payment terms and segment in its meta; contacts are individuals with the company as parent.
- **Contract prices:** the cart applies the price list when hydrated with the company. Discovery prices don't, so product cards and pages read the company's price list on the server from the Catalogue API: `priceList(identifier) { productVariants(language, first) { edges { node { sku priceVariant(identifier) { priceList(identifier) { modifier modifierType } } } } } }`, paged until an empty page (`hasNextPage` stays true). Apply by `modifierType`, or use `priceFor(count, customerIdentifiers: [company])`, which applies volume tiers too. Round for display, and cache per company.
- **Recipes that sell their ingredients:** "Order all ingredients" adds one case of each linked product; portions scale the quantities. Product pages list the recipes they're used in.
- **Reorder** puts a past order back in the cart. **Recommendations:** the company's most-ordered products, plus the other ingredients of recipes using what's in the cart.
- **Taste ranking:** a `taste` vocabulary over cuisine, product type, main ingredient and occasion. `setItemTaste` for every product (it empties the variant components, so rewrite the pack fields), `publishItem` per item and language, then `igniteDiscoApi(stacks: opensearch)` and poll until complete. Send `context.userTaste: [{ vocabulary: taste, weights, magnitude }]`. A company's taste mixes chosen preferences (0.6) with the topics of its order history (0.4), top 12 keys. Rank with `tasteCosine` plus a 0.25 boost on sales velocity; similar products with `nearestTo`.
- **Preview:** a draft route registered as a custom preview view in the Crystallize App.
- **SEO and agents:** hreflang, Product and Recipe JSON-LD, sitemaps per language, `llms.txt`, and every page as Markdown.
- Env: `CRYSTALLIZE_TENANT_IDENTIFIER`, `CRYSTALLIZE_ACCESS_TOKEN_ID`, `CRYSTALLIZE_ACCESS_TOKEN_SECRET`, `NEXT_PUBLIC_SITE_URL`.

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

- In mass operations, get item ids with `fetchItemByResourceIdentifier … 'itemId'`; `valueOf … 'id'` returns the document id.
- An upsert replaces all components. A numeric with 0 decimal places is rejected. The Core API pages at 100.
- A mass-operation topic subtree is capped at 30 topics; create large maps through the Core API.
- Chunks with translated text must be multilingual, or one language overwrites the others.
- `publishItems` is async and can hide failures: publish per item and language. An empty numeric piece blocks publishing unless you pass `disableComponentValidation: true`.
- Discovery: never pass explicit `null`; filter on topics or parent paths, not on name patterns; name-autocomplete filters return score-0 hits in no useful order, so pair them with `term` and sort by score; relations inside chunks come back in the default language.
- Shop API: the JWT expires; `hydrate` replaces the cart; `taxRate` is a fraction; use `decimals: 4` and round half up for display; `place` locks the cart.
- Price lists: `build-mass-operation` drops unknown fields silently, so check the real shape with the MCP.
- Arguments to cached calls must be stable (sort arrays). Retry Discovery on 429 and 5xx.
- 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.