By Steve Merrill, Founder of WRKNG Digital | August 15, 2026
Run these nine checks and you will know, today, whether ChatGPT Shopping, Google AI Overviews, and Perplexity can find, read, and recommend your Shopify products. Each check is the same pattern: what to look at, why it matters, and how to fix it. Start at the top and work down.
Here's the bottom line. AI assistants do not guess. They read structured data, product feeds, and clean text. If those signals are broken, you are invisible when a buyer asks AI what to buy.
1. Confirm your product pages have valid Product structured data
Paste a product URL into Google's Rich Results Test and see if it detects a Product item with no errors. This markup is how machines understand that the page is a real product, not a blog post. If it fails, your theme's schema is broken or missing, and you fix it in the theme's product template or with a dedicated schema app.
2. Check that price, availability, and GTIN are in your schema
A Product schema with no price or stock status is a half-answer that AI will not repeat. Schema.org's Product spec expects an offers block with price, priceCurrency, and availability, plus a GTIN or MPN when you have one. Open the page source, search for "offers," and confirm those fields carry real values.
3. Audit your Google Merchant Center product feed fields
Google AI Overviews and Shopping pull heavily from your product feed, far more than your pages. Google's product data specification lists required fields like title, description, price, availability, and image link. Log into Merchant Center, check the Diagnostics tab, and fix every disapproved or flagged item before the traffic spikes.
4. Add a real FAQ block with definition-style answers
AI models cite short, direct answers to real questions. Add an FAQ section to your most-viewed product and collection pages that answers what buyers actually ask, in one or two plain sentences each. Write the answer first, then the detail, because that is the format assistants lift word for word.
5. Publish an llms.txt file at your root domain
An llms.txt file is a plain-text map that points AI models to your most important pages, described at llmstxt.org. This is an emerging convention, not a requirement, and it costs almost nothing to publish. Add your bestsellers, top collections, and main policy pages so assistants get a clean route into your catalog.
6. Verify your sitemap lastmod dates are honest and fresh
Crawlers use the lastmod date in your sitemap to decide what to re-fetch. Google Search Central says lastmod only helps when the date is accurate, and fake or frozen dates get ignored. Shopify generates your sitemap at /sitemap.xml automatically, so open it and confirm updated products actually show recent dates.
7. Make sure AI crawlers are not blocked in robots.txt
If you blocked bots in a panic last year, you may be hiding your store from the exact systems buyers now use. Open yourdomain.com/robots.txt and check that agents like GPTBot, Google-Extended, and PerplexityBot are not disallowed on your product paths. Shopify lets you edit robots.txt through a theme file, so unblock what you want indexed.
8. Test a real buyer question in ChatGPT and Perplexity
Ask ChatGPT and Perplexity the exact question a customer would ask before buying your product, like "best waterproof hiking boots under $150." See if your store shows up, if a competitor shows up, or if nothing does. This is the only check that tells you what the buyer actually sees.
9. Fix thin or missing product descriptions
A one-line description gives AI nothing to understand or quote. Write descriptions that name the material, the use case, the size or fit, and who it suits, in plain sentences. That text feeds both your schema and your feed, so fixing it once improves several checks above at the same time.
How We Chose This List
Every check maps to a real mechanic that AI shopping systems read: structured data, product feeds, crawlable text, and freshness signals, all documented by Shopify, Google, OpenAI, and Schema.org. We ordered them so the highest-impact, do-it-today fixes come first.
FAQ
Q: How do AI shopping assistants find my Shopify products?
They read your product structured data, your Google Merchant Center feed, and your on-page text. If those signals are missing or wrong, the assistant skips your store and recommends someone else.
Q: Does Shopify add Product schema automatically?
Some themes add basic Product markup, yet many miss price, availability, or GTIN. Validate every template with Google's Rich Results Test rather than assuming your theme handles it.
Q: What is an llms.txt file and does my store need one?
This is a plain-text file at your root domain that points AI models to your most important pages. Think of it as an emerging convention, not a rule. It costs almost nothing to publish and gives assistants a curated map of your store.
Q: How soon before the holidays should I run these checks?
Run them now. Structured data, feeds, and content take days to weeks to get re-crawled, so fixing them in August gives AI systems time to trust your data before peak shopping.
Want a team to run all nine checks on your store and fix what is broken before the surge? See how we do it on our agentic commerce page.
Steve Merrill
Founder, WRKNG Digital
August 15, 2026
