Catalog quality
Know exactly how AI-ready your catalog data is
Two scores, read from your own catalog, that tell you how eligible your products are for AI shopping search and how current the data agents read actually is. Completeness scores the fields Shopify normalizes on (category, GTIN, attributes, brand). Freshness scores how recently we refreshed your AI-readable layer. Both sit under a plain map of what each number proves, so a score we verified from your data is never dressed up as a guarantee we can't make.
See it, don't take our word
Your catalog, scored from your own data
Completeness and freshness are computed from your products, not a benchmark. Each pillar shows its coverage, so you can see the one lever that moves your score most.
An example. Every figure is your own catalog's data. There is no cross-merchant benchmarking and no peer comparison.
Completeness: the eligibility you control
AI shopping search can only recommend a product it can read. Completeness scores the fields that decide that, weighted by how much each matters: your Standard-Taxonomy category (the anchor Shopify normalizes on), GTIN or barcode (what clusters your product onto the shared cross-store listing so you compete on it instead of being invisible), attributes, and brand. One 0 to 100 number, with each pillar's coverage broken out and the weakest one flagged as your biggest lever.
It is honest by construction. A pillar is only scored over the products where the field was actually observable, so we never imply we checked something we didn't, and the card says so when a field wasn't measured. Every figure comes from your own catalog. There is no peer comparison.
Freshness: is the data agents read up to date?
A complete catalog still goes stale. Freshness scores how recently we refreshed the AI-readable layer agents see, per surface: products, and content like collections and pages. Two signals feed it. Lag is how long since the last successful sync. Drift is recent failed syncs, which mean changes that never made it into the layer, so it is actively diverging from your live store rather than just aging.
The result is a plain read on whether what an assistant sees matches what you're actually selling today, with the oldest surface called out so you know where a refresh is overdue.
Three tiers, so a number never means more than it should
The catalog page groups everything into three never-blended tiers, each labeled with what its numbers actually prove. Eligibility we verify is measured from your own data, the levers you control, and it's where completeness and freshness live. Presence we observe is point-in-time readings of Shopify's Global Catalog: real, but what we saw when we last checked, not a guarantee of what an assistant returns this second. External truth we link is everything we can't verify from inside your store, where we point you to the source instead of claiming it ourselves.
Most tools blur these together and quietly overclaim. Keeping them separate is the point: you always know whether a number is something we proved, something we observed, or something to go check at the source.
Frequently asked questions
How is the catalog completeness score calculated?
It's a weighted coverage score over your own products across four pillars: taxonomy/category (the heaviest, since it's the catalog's normalization anchor), GTIN/barcode, attributes, and brand. Each pillar is scored only over the products where that field was observable, and the weakest pillar is flagged as your biggest lever. It's computed from your catalog, never a comparison to other stores.
What does the freshness score measure?
How current the AI-readable layer we maintain for your store is. Per surface (products and content) it combines lag, the time since the last successful sync, with drift, recent failed syncs that mean changes never landed. A fresh, fully-synced catalog scores high; one that hasn't synced in days, or is failing, scores lower.
Do these scores compare me to other stores?
No. Both scores are read entirely from your own catalog and sync history. There is no cross-merchant benchmarking and no peer ranking in catalog quality. They measure your eligibility and your data's recency against what AI search needs, not against anyone else.
What are the three provenance tiers?
A way of being honest about what each number proves. Tier 1, eligibility we verify, is measured from your own data (completeness and freshness live here). Tier 2, presence we observe, is point-in-time readings of Shopify's Global Catalog. Tier 3, external truth we link, is what we can't verify ourselves and point you to the source for. They're never blended, so a verified score is never read as a guarantee.
Related features
See where you rank in Shopify's Global Catalog, fix the product data holding you back, and prove the lift as AI agents pick you up.
Product, FAQ, local business, and breadcrumb schema generated from real store data and kept honest.
Ask AgentReady inside Shopify's Sidekick assistant: your AI-search rank, catalog gaps, and readiness score, right where you work.
Make your store readable to AI agents
Free to install, AI-readable in about ten minutes, with the proof in your dashboard.