Meeting Google's and OpenAI's product requirements still won't get you recommended

Ask an AI assistant for “a carbon steel pan that works on induction, under $100” and it answers with two or three specific products. To be one of them, your product has to be easy for AI to read: the assistant needs to know what it is, who it fits, and how it compares, without inferring any of it from marketing copy.

Both Google and OpenAI publish exactly what they read. It's worth working from those lists rather than from guesses.

Two ways in

A product reaches an AI answer through one of two doors.

• Your product pages. Search engines and AI send programs called crawlers to read each product page, including its structured data: hidden code that labels facts like price and size. This is what Google AI Overviews, Perplexity, and ChatGPT's web search work from.
• A product feed. A file you send that lists all your products: prices, stock, and product codes. ChatGPT's shopping results draw on feeds like this.

The two overlap heavily. A catalog that's complete enough for one is usually close for the other.

What Google requires

For a product page to show up in Google's shopping results, Google lists five required fields in that product page's structured data:

• name — the product name
• image — a product photo
• offers — the price and buying details, grouped together
• offers.price — the active price
• offers.priceCurrency — the currency, as a three-letter code like USD

Most Shopify themes, the design templates stores use, add those five on their own. They get you into the listing; they don't say anything about the product.

The recommended list is where the detail lives, and it maps almost one to one onto the questions shoppers ask:

• material, color, size — what it's made of, what it looks like, whether it fits
• audience — who it's for
• gtin, mpn, sku — product codes (barcode number, maker's part number, your own stock code) that let an assistant match your product to the same product elsewhere
• availability, itemCondition, shippingDetails, hasMerchantReturnPolicy — whether it can actually be bought, and on what terms
• aggregateRating, review — what other people said
• inProductGroupWithID — which sizes and colors belong to the same product

The full list, with the exact formats, is in Google's merchant listing documentation.

What ChatGPT's feed requires

OpenAI's rules for product feeds ask for nine required fields per product:

• item_id, title (up to 150 characters), description (up to 5,000)
• url, image_url, brand, seller_name
• availability — one of in_stock, out_of_stock, pre_order, backorder, unknown
• price — amount and currency together, like 79.99 USD

A product's sizes and colors are grouped with group_id and described with variant_dict. Product codes like gtin and mpn are optional, but they let AI check your feed against other sources. OpenAI has published the full rules.

On Shopify, there is a step before both. ChatGPT, Microsoft Copilot and Google AI Mode get your products from Shopify Catalog, and some products never make it in. Here is what gets a product left out of Shopify Catalog.

Required gets you listed. Comparable gets you recommended.

This is the part that catches people out. A listing can satisfy every required field and still never be recommended, because nothing in it answers the question that was asked.

“Works on induction” is not a field. An assistant arrives at it from a material, a note about the base, a use case in the product description, maybe a review that mentions an induction stove. “Good for beginners” comes from care notes or review text. “Under $100” comes from the price, which is the one part most stores already get right.

So the useful question isn't “does my code pass Google's test?” It's “if someone described this product back to me from my own data alone, would they describe it accurately, and would they be able to compare it to the next one?”

Checking your own store in ten minutes

1. Open a product page, view its source code (right-click, then "View page source"), and search for ld+json. That's where the structured data sits. Confirm you have a Product section with name, image, price, and currency.
2. Paste the product page's web address into Google's Rich Results Test and read the warnings, not just the errors. Warnings are the recommended fields you're missing.
3. Read the product description as if you'd never seen the product. Does it say what it's for, who it fits, and what it's made of? Or does it say “engineered for performance”?
4. Check two sizes or colors of the same product. Do they share a group ID, or do they look like two unrelated products?
5. Pick your three best sellers and ask ChatGPT and Perplexity a question those products should win. Note what gets recommended instead, and why that listing is easier to read than yours.

The last step is the one that tends to change minds. It's also the first thing we do on a call.

What this doesn't do

Complete product information makes a product eligible and easy to read. It doesn't guarantee a recommendation: assistants weigh reviews, brand familiarity, price, and their own quirks, and none of that is under your control. Google's AI Overviews, in particular, only see a change after Google visits your product page again.

What you can control is whether an assistant has to guess. Most catalogs make it guess.