How to check if ChatGPT can read your Shopify store (and what to fix if it cannot)

The 30-second test anyone can run#

Start with two quick checks before you change anything.

First, open ChatGPT and ask it to recommend stores or products in your category, the way a customer would. Try a few phrasings. Note whether you show up, whether competitors show up, and whether the answer cites any sources. This tells you what the engine currently knows, not why, but it sets your baseline.

Second, open your store's robots.txt in a browser. Type yourstore.com/robots.txt and read it. You are not looking for a default block, because Shopify does not ship one. You are confirming that the AI search crawlers are not being disallowed by a rule on your store. If you see broad Disallow lines, or rules that name AI crawler user-agents, note them. That is the thread to pull. If the file looks clean and does not disallow those crawlers, the problem is likely somewhere else, and the later sections cover where.

Keep this in perspective. The robots.txt check confirms access. It does not by itself decide whether AI engines recommend you. It rules a common, fixable cause in or out.

The GPTBot mistake#

Most advice you will find says "allow GPTBot" and stops there. That is the wrong fix, because GPTBot is not the bot that gets you into a ChatGPT answer.

Here is what each OpenAI crawler actually does, from OpenAI's own documentation.

GPTBot is used to crawl content that may be used to train OpenAI's foundation models. It is training only. Allowing GPTBot does not get you cited in live ChatGPT answers, and disallowing it only signals that your content should not be used for training.

OAI-SearchBot is OpenAI's search crawler. It surfaces sites in ChatGPT's search features. Sites that are opted out of OAI-SearchBot will not be shown in ChatGPT search answers. OpenAI recommends allowing it in robots.txt so your site can appear in search results. This is the crawler that controls ChatGPT search inclusion. If you only take one thing from this guide, make sure OAI-SearchBot is allowed.

ChatGPT-User is a user-triggered fetch, used when someone asks ChatGPT a question and it visits a page. It is not used for automatic crawling, robots.txt rules may not apply to it, and OpenAI states it is not used to determine whether your content appears in Search. For managing search appearance, the bot that matters is OAI-SearchBot.

The other engines have their own crawlers. PerplexityBot is Perplexity's crawler. ClaudeBot is Anthropic's crawler. Google-Extended is Google's control for whether your content is used to train and ground its AI models, which is separate from how you rank in Google search. The same first step applies across all of them: confirm none are disallowed in your robots.txt.

The takeaway. Allowing GPTBot is not what gets you cited in ChatGPT. The crawler that governs ChatGPT search inclusion is OAI-SearchBot. Check that one first.

Is your robots.txt actually the problem#

Often it is not, and it helps to know that before you start editing.

Shopify's default robots.txt does not block AI crawlers. The customization file, robots.txt.liquid, is not included in themes by default and has to be added before you can change anything. So a brand-new store on a standard theme is not blocking these crawlers out of the box.

When a store does end up blocked, it is usually one of three things. The first is a theme-level customization, where someone added a robots.txt.liquid template and wrote rules that disallow more than intended. The second is leftover development or password protection, where a store is still gated from launch or staging and crawlers cannot reach it at all. The third is a blanket Disallow rule that was meant for something else and happens to catch AI bots along with it.

If your test in the first section showed broad Disallow lines or named crawler rules, this is where the fix lives. If your robots.txt is clean, move to the next section, because the cause is probably not access at all.

The silent failure robots.txt cannot show you#

You can have a perfect robots.txt and still be unreadable. Here is why.

AI crawlers generally do not execute JavaScript. If your product name, price, and description are rendered client-side, meaning they are loaded into the page by JavaScript after the initial HTML arrives, a crawler that does not run JavaScript may never see them. Crawling is allowed, but the content is effectively invisible.

You can check this yourself in a minute. Open one of your product pages, right click, and choose View Page Source. This shows the raw HTML the server sent, before any JavaScript runs. Search that source for your product name, your price, and a line from your description. If they are present in the source, a crawler can read them. If they only appear when you use Inspect or Elements, or not at all in the raw source, they are being injected by JavaScript, and that is the gap to close.

This one matters because it is invisible to the robots.txt check. A store owner can confirm crawlers are allowed, see no block, and still not understand why nothing improves. The content layer is the reason.

How to fix crawler access on Shopify, correctly#

If your robots.txt is disallowing AI crawlers and you need to change it, here is the Shopify-documented path.

Go to Online Store, then Themes. Find your theme, open the menu marked with three dots, and choose Edit code. Under Templates, choose Add a new template, select robots, and choose Create template. This creates the robots.txt.liquid file. From there you edit it with Liquid to adjust the rules.

Read this part before you touch it. Shopify treats editing robots.txt.liquid as an unsupported customization, and Shopify's own guidance is that incorrect use can cause a loss of traffic. So back up your current setup first, change one thing at a time, and if you are not comfortable in Liquid, work with a Shopify Partner. A bad robots.txt edit can do more harm than the original problem.

If your issue was leftover password protection rather than a robots rule, the fix is different and simpler: remove the store password under Online Store preferences once you are ready to be public.

What to check next, ranked#

Crawler access is the first layer, because if the crawler cannot reach or read your store, nothing else matters. Once access is clean, two more layers decide whether AI engines can actually understand and recommend your products.

The next layer is structured data. Structured data is among the strongest known signals for AI product visibility, with the strongest evidence for ChatGPT and Perplexity and a more mixed picture for Google AI Overviews. The question is whether your JSON-LD is present in the raw HTML and complete enough for an engine to trust.

The last layer is product data completeness, the specific fields the models match against, like brand, price, availability, and identifiers. Gaps here are why a technically reachable store still does not get recommended.

That is the order to work in: access, then schema, then product data. ShelfScore runs all three as one layered diagnosis, gives you a single score, and ranks the fixes by impact with the header showing "Up to +N pts recoverable," so you fix the highest-impact gaps first instead of guessing.

Frequently asked questions#

Why does ChatGPT recommend my competitors and not me? It can be one of several things, and the point of this guide is to separate them. The common, checkable causes are crawler access (the AI search crawler is disallowed or the store is still gated), content that is invisible because it renders in JavaScript, and thin or missing structured data and product fields. Run the checks above in order to find which applies to your store.

Should I just allow GPTBot to show up in ChatGPT? No. GPTBot is OpenAI's training crawler. Allowing it does not get you cited in live ChatGPT answers. The crawler that controls whether you appear in ChatGPT search answers is OAI-SearchBot, so confirm that one is not disallowed.

Does Shopify block AI crawlers by default? No. Shopify's default robots.txt does not block AI crawlers, and the robots.txt.liquid customization file is not included in themes by default. When a store is blocked, it is usually from a theme-level customization, leftover password protection, or a broad Disallow rule, not the default.

My robots.txt looks fine, so why am I still not showing up? Crawling can be allowed while your content is still unreadable. AI crawlers generally do not execute JavaScript, so product data that loads client-side may not be visible to them. Use View Page Source on a product page and confirm your product name, price, and description are in the raw HTML.

Is it safe to edit my robots.txt on Shopify? Edit with care. Shopify treats robots.txt.liquid as an unsupported customization and warns that incorrect use can cause a loss of traffic. Back up first, change one rule at a time, and work with a Shopify Partner if you are not comfortable editing Liquid.

Do I need to do this for Perplexity and Google too? The same logic applies. Each engine has its own crawler, such as PerplexityBot for Perplexity, ClaudeBot for Anthropic, and Google-Extended as Google's AI training control. Confirm none of them are disallowed in your robots.txt if you want to be readable across those engines.

Sources#

• OpenAI, Overview of OpenAI Crawlers (developer documentation), for the roles of OAI-SearchBot, GPTBot, and ChatGPT-User. Fetched 2026-05-30.
• Shopify Help Center, editing robots.txt.liquid, for the default behavior, the template not being included by default, the edit path, and the unsupported-customization caveat.
• Shopify newsroom, Winter '26 Edition Agentic Storefronts announcement, December 10, 2025, for agent-ready-by-default framing.
• Structured-data evidence: structured data is among the strongest known signals for AI product visibility, strongest for ChatGPT and Perplexity, mixed for Google AI Overviews. ShelfScore does not claim structured data makes a store binary visible or invisible; it identifies the issues most likely to limit AI visibility.