By Steve Merrill, Founder of WRKNG Digital | August 26, 2026
ChatGPT recommends products it can read, trust, and match to a shopper's exact question. If your product data is thin or your store hands AI a wall of boilerplate HTML, you never enter the conversation.
I've run more than 40 AI-readiness audits on Shopify stores this year. Most of them are invisible to ChatGPT right now. Not because their products are bad. Because their data is unreadable.
Here's how to fix that.
Why does ChatGPT recommend some products and ignore others?
ChatGPT recommends products when it can pull clean, structured data about them and connect that data to a shopper's intent. It leans on product feeds, structured markup, and partner catalogs. When those signals are missing, your store gets skipped.
OpenAI has been building shopping directly into ChatGPT, including product results and a checkout flow with partners. Shopify confirmed a connection that lets merchant catalog data reach ChatGPT through the Shopify platform. That pipe only carries data that's actually there. Blank fields carry nothing.
Think about what the model needs. A price. A real title. Materials. Sizes. Who it's for. If a human shopper would ask it, the AI needs it in your data.
What product data does ChatGPT actually need?
ChatGPT needs the same attributes a good salesperson would rattle off: an accurate title, a specific description, price, availability, brand, and category. The more of these you fill with real detail, the more questions your product can answer.
Most stores stop at a title and two sentences. That's the problem. A title like "Blue Jacket" tells AI nothing. "Men's Waterproof Insulated Winter Jacket, Recycled Nylon" tells it who it's for, what it does, and what it's made of.
Google publishes a full product data spec that maps closely to what AI systems want to see. Read the Google Merchant product data specification and treat it as your minimum bar. Fill gender, age group, material, color, and size on every variant.
How do you structure your store so ChatGPT can read it?
Add Product schema in JSON-LD to every product page, with name, description, brand, offers, price, and availability filled in. This is the machine-readable version of your product, and it's the fastest signal for AI to parse.
Schema.org publishes the Product schema reference. Your theme may output part of it already. Most output a shell with empty fields. I've seen stores with valid schema markup and no price inside it. Useless.
Cut the boilerplate too. When 90% of your page HTML is navigation, popups, and app scripts, the model has to dig for the 200 words that matter. Dense, substantive product copy wins.
Does connecting your Shopify catalog to ChatGPT help?
Yes. Shopify's catalog connection with OpenAI is the most direct path for merchant product data to reach ChatGPT's shopping results. If your Shopify plan and settings support it, turn it on and confirm your feed is complete first.
A pipe is only as good as what flows through it. Connecting a half-empty catalog just sends AI a half-empty catalog. Fix the data, then open the connection.
We did this on a client's store last month. Their feed had material and age-group blank on 70% of products. We filled them, then confirmed the catalog sync. The point isn't the toggle. It's the data behind it.
How do you check if ChatGPT can see your products?
Ask it. Open ChatGPT, describe a shopper looking for exactly what you sell, and see whether your store or products come up. Then ask a more specific version with a material, price range, or use case. Watch where you fall out.
Do this for five real buyer questions. If you never appear, that's your baseline. Run the same test after you fix your feed and schema, and you'll see the gap close.
This is the same read we give stores in a WRKNG audit. What AI sees, what it says, and where your data lets you down.
Frequently Asked Questions
Can any Shopify store get recommended by ChatGPT?
Yes. There's no paid gate to be recommended. ChatGPT recommends products it can read and match to a shopper's question, so complete product data and clean schema are what get you in, regardless of store size.
How long does it take to show up in ChatGPT after fixing my data?
It varies. Structured data and feed changes need to be recrawled and synced before AI systems reflect them, which can take days to a few weeks. Fixing data is a prerequisite, not an instant switch.
Do I need special apps to be visible to ChatGPT?
No. The core work is complete product data, Product schema, and a clean catalog connection. Apps can help fill schema or feeds, but the data quality is what matters.
Is this the same as SEO?
It overlaps but isn't identical. SEO targets search rankings. Getting recommended by ChatGPT targets machine-readable product data and citations. Good structured data helps both.
Want to know if AI assistants can actually find and recommend your store? Get a free AI-visibility read on your Shopify store at WRKNG Digital. We show you exactly what ChatGPT, Perplexity, and Google AI see when they look at your products.
