Capture · Product Catalog
The product data foundation your AI was missing.
Personalization stops at "who" without a model of "what." Flash adds an AI-ready catalog that flexes to your vertical— serialized luxury pieces, apparel size matrices, F&B combos — synced from your ERP and Shopify, and wired to every order line so your segments and agents finally reason about products, categories, and brands.
The problem
You know your members. You can't personalize on what they buy.
You can’t tell what they’ll buy next
You know who your members are — but not what to put in front of them. With no product, category, or brand affinity on the profile, next-best-product, cross-sell, and replenishment timing are guesswork.
One model can’t fit every vertical
Jewelry needs per-item serials, apparel needs size matrices, F&B needs combos. Generic catalogs force you to bend your business to the tool.
Your AI has nothing to read
A consumer bot can’t answer “is this gluten-free?” or “what size should I get?” with no specs, no size guides, no grounding content per product.
Industry models
One catalog that flexes to how your industry really sells.
Not a separate system per industry — a small set of flexible building blocks plus custom attributes, so a new industry needs no rebuild. Each model below is live in the product today.
Per-item serial numbers
Every physical piece is tracked individually — its own serial number, authenticity certificate, and details (carat, metal, movement), with ownership recorded at sale.
Size and color variants
Every size-and-color combination as its own sellable variant — the fit and return detail your stylists and AI need to recommend the right size.
Combos & modifier groups
Build-your-own meals: a parent product composed of required components and optional modifier groups (choose-a-side, add-a-drink) with per-option upcharges.
Brand · category · price lists
Hierarchical categories, brands, tiered/regional price lists, inventory by store or warehouse — the breadth a multi-category catalog needs.
AI infrastructure
Built so your agents and bots can reason about products.
One complete catalog
Products, variants, serial-numbered items, components, media, content, inventory, price lists, collections, and itemized orders — one unified model, scoped to your team.
Synced from your systems
ERP, Shopify, or any middleware pushes products by its own ID; Flash updates without duplicates and never writes back. One simple import.
Content your AI can read
Every product carries rich descriptions, specs, FAQs, size & care guides, and certificates — the knowledge a customer-facing AI bot reads to answer product questions. Browse it through the AI tools or the in-app catalog console.
Category-level metrics & personalization
Every order ties back to product, category, and brand — powering sales-by-category/brand and top-product metrics, plus affinity tags (multi-category shopper, purchased-category) for segments and AI.
Next-best-product recommendations
A co-purchase engine ("members who bought X also bought Y") plus category affinity produces personal next-best-product picks for each member — shown in email through the Recommendations block (nothing to connect), available to AI agents, and over the API.
Synced from your systems
Your ERP stays the source of truth.
You don't re-key products into yet another system. ERP, Shopify, or any middleware pushes products, variants, categories, brands, and inventory keyed by its own ID; Flash updates without duplicates and never writes back. Shopify products map in automatically — images and rich descriptions included.
One simple import endpoint
POST /api/v2/catalog/import
{ "source": "erp",
"brands": [...], "categories": [...],
"products": [...], "variants": [...],
"inventory": [...] }Idempotent by (team, source, external_id). A bad row is reported in errors[] — it never aborts the batch. Read back via GET /api/v2/products,/categories,/brands.
Recommendations
Know what each member buys next.
Once orders carry their line items, a next-best-product engine turns purchase history into picks for each member. Two signals, combined and always excluding what they already own: co-purchase(“members who bought this also bought…”, refreshed nightly) and category affinity (top sellers in the categories they already shop). No history, no guesses — recommendations are grounded in real behavior.
On the member profile
Each member's Products tab shows what they bought, their favorites, and “they may like” picks — so your team acts with context.
In campaigns
Add the Recommendations block to an email — each recipient automatically sees their own picks (image, price, and a link to the product page). Powered by the built-in engine, with nothing to connect or pick.
For AI agents & code
Agents and your own apps read each member's picks through Flash's AI tools and API. Same engine, every surface.