How AI readsyour store
Updated October 2026
- ChatGPT
- Claude
- Gemini
- Perplexity
Key takeaways
- Before it reads, the assistant searches a search engine's index, and they don't all use the same one: a store that isn't in that index doesn't exist for it.
- The visible text on the product page reached all four assistants: ChatGPT, Claude, Gemini and Perplexity.
- JSON-LD in the HTML the server sends reached Gemini only. Google and Bing read it for search, as their own documentation says.
- Schema added by a script or Google Tag Manager after the page loads reached none of the four.
- No assistant requested llms.txt during the test.
When someone asks an AI assistant to look at a product, the assistant opens the product page right then and answers with what it receives. ChatGPT, Claude and Perplexity receive the page the shopper sees, not the structured data; Gemini receives both, and markup added by a script reaches none of them.
That's the short answer to the question every store working its catalog for AI search asks: of everything I put on a product page, which part actually reaches each assistant? We didn't take it from each company's documentation or from an opinion. We measured it in October 2026, with a code hidden in every spot on the page, and the whole table is here, what gets through and what doesn't.
Before it reads: where each assistant searches
For almost any product question, the assistant doesn't start with your store. It first searches a search engine's index, picks a few results and only then opens those pages. It's the rule that always held on Google: a store that isn't in the index doesn't exist for the assistant, however well its product page is written. The path has four steps:
- Memory. From its training, the model already knows the brands that are cited everywhere. A small store can't change that.
- Search. It queries a search engine's index. If the product page isn't indexed, it doesn't come up.
- Selection. It picks a few results by indexing, authority and relevance.
- Reading. It opens those pages and reads a reduced version of each one. That's the part this study measures.
That's why ecommerce SEO is still the base of GEO and AEO. And since each assistant searches a different index, ranking well on Google says nothing about Copilot or Claude.
| Assistant | Index it searches | How we know |
|---|---|---|
| Gemini, AI Overviews and AI Mode | Google Search's index | Google documents it[1]Google Search Central. Optimizing your website for generative AI features on Google Search |
| Copilot | Bing's index | Microsoft documents it[2]Microsoft Advertising. Optimizing Your Content for Inclusion in AI Search Answers |
| Claude | Brave Search | An analysis by Profound: 13 of the 15 results Claude cited matched Brave's top results[3]Profound. What Is Claude Web Search? Explained |
| ChatGPT | Its search, where OAI-SearchBot surfaces websites | OpenAI documents it; a site that blocks OAI-SearchBot doesn't show in its search answers[4]OpenAI. Overview of OpenAI Crawlers |
| Perplexity | Its own results, where PerplexityBot surfaces websites | Perplexity documents it[5]Perplexity. Perplexity Crawlers |
Claude's row is the weakest in the table: it comes from a small sample, from March 2025, and Anthropic hasn't confirmed it. Still, it points at a gap few stores check. A store that's on Google and Bing may not be on Brave. Google and Bing have dashboards to submit the sitemap and report changes, Google Search Console and Bing Webmaster Tools; Bing also accepts IndexNow, up to 10,000 URLs per notice.[6]IndexNow. IndexNow documentation Product pages can't be submitted to Google one by one: its Indexing API only takes job postings and livestreams.[7]Google for Developers. Indexing API Quickstart Brave has no dashboard, no sitemap submission and no IndexNow. Its index is fed by its own crawler and by the Web Discovery Project, through which Brave browser users who opt in share the pages they visit anonymously, and its submission form is for asking it to read a page again.[8]MERJ. How Brave Search discovers new pages A product page nobody visits with Brave can stay out of its index.
How we measured it
We built test product pages and hid a unique code in each of the 16 places a fact can sit on a page: the visible text, the title, the image's alt text, the JSON-LD in the HTML, JSON-LD added by JavaScript or Google Tag Manager, microdata, the meta description, the noscript block, content drawn by JavaScript, llms.txt and a few more. The codes were made up for the test and exist nowhere else on the internet. If one shows up in an assistant's answer, the only place it could have come from is that part of that page.
Then we asked each assistant about the product: 210 conversations per assistant and model, in three modes. In one, the assistant decides whether to open the URL; in another, we ask it to open it; in the third, it gets no URL at all. We measured through each company's API, not in their apps: ChatGPT with gpt-6-luna; Claude with Sonnet 5.5 through the API and with Claude Code on a subscription; Gemini with three models, 3.1 Pro, 4 Argon and 3.8 Flash; and Perplexity with its Agent API.
A test like this only counts if it can fail, so it has controls. The visible text is the positive control: if an assistant doesn't bring it back, that conversation didn't read the page. A decoy code we never published didn't appear once, so the assistants aren't making codes up. The runs with no URL scored 0%: none of this was known to them beforehand. And the server logs name the robot behind each visit: ChatGPT-User, Claude-User, GoogleAgent-URLContext and Perplexity's browser. Every percentage carries its margin of error (a 95% Wilson interval), and each arm of the test (an assistant, a model and its tool for reading pages) is counted on its own, never pooled. We measured on October 22, 23 and 29, 2026; we voided Gemini's run of the 23rd because the pages carried the nosnippet directive, and ran it again without it.
The results
Each cell under the four assistants is the share of conversations in which the code from that spot made it into the assistant's answer. The table covers nine of the sixteen places we measured. The first column isn't our measurement: it's what Google and Bing document they do with each part when they index.
| Where the fact is | Google and Bing, when indexing | ChatGPT | Claude | Gemini | Perplexity |
|---|---|---|---|---|---|
| Visible text | Used | 100% | 88–97% | 98–100% | 100% |
| Title | Used | 84% | 88–97% | 98–100% | 100% |
| Image alt text | Google Images | 100% | 88–97% | 98–100% | 0% |
| JSON-LD in the HTML the server sends | Rich results and Shopping | 0% | 0% | 97–100% | 0% |
| JSON-LD added by JavaScript or GTM | Google processes it, less reliably for Shopping | 0% | 0% | 0% | 0% |
| Markup in microdata | Used | 0% | 0% | 0% | 0% |
| Meta description | Used in the search result | 0% | 88% API, 0% Claude Code | 0% | 0% |
| Content drawn by JavaScript | Google renders it | 0% | 0% | 0% | 100% |
| llms.txt | Google doesn't need it | 0 requests | 0 | 0 | 0 |
Three places reached no assistant at all: JSON-LD added by a script, microdata and llms.txt. In Claude's column, the range runs from the API (88%) to Claude Code (97%), and the meta description reached the API (88%) and not Claude Code (0%). Gemini's three models behaved the same.
What it means for each assistant
ChatGPT
ChatGPT gets the text of the page as the server sends it: the visible text and the image alt text arrived in 100% of conversations, and the title in 84%. In the test it didn't run JavaScript, so content drawn by a script didn't reach it, and none of the markup did either: not the JSON-LD, not the microdata, not the meta description. The visit comes from ChatGPT-User, the user agent OpenAI uses when a person asks it to open a page.
Claude
Claude reads like ChatGPT where it counts: the visible text, the title and the alt text reach it, from 88% through the API to 97% in Claude Code, and the JSON-LD reaches it through neither. The difference is the meta description: it reached Claude through the API in 88% of conversations and Claude Code in none. It's the only one of the four the meta description reached, and only through one of its two routes, so it's not a good place to tell an assistant anything. The visit comes from Claude-User.
Gemini
Gemini is the only one of the four that receives the JSON-LD: in 97% to 100% of conversations, as long as the block is in the HTML the server sends. JSON-LD added by JavaScript or Google Tag Manager after the page loads didn't reach it, and neither did microdata. The visible text, the title and the alt text reached it in 98% to 100%. All three models behaved the same, and the visit comes from GoogleAgent-URLContext.
Perplexity
Perplexity reads with a real browser that runs JavaScript: it's the only one that received content drawn by a script, in 100% of conversations. Even so, JSON-LD added by a script didn't reach it, nor did the JSON-LD in the HTML, nor the image alt text. The visible text and the title reached it every time. One caveat: Perplexity's Agent API runs on an OpenAI model under the hood, so this column describes how Perplexity reads the page, not a Perplexity model of its own.
What it means for your product pages
Assistants read your page like a shopper in a hurry: if a fact isn't in view, it doesn't exist. The table leads to six decisions for a product page.
Write what matters on the page. The price, the dimensions, the materials, what it's compatible with, what's in the box: if it's in the visible text, it reaches all four assistants. A visible FAQ counts as visible text. Anything that lives only in an image's alt text doesn't reach Perplexity.
Put the JSON-LD in the HTML the server sends. It's what Google and Bing read for search: Google documents which properties product markup needs for its merchant listings,[9]Google Search Central. How To Add Merchant Listing Structured Data and Bing confirmed that it reads Schema.org markup in JSON-LD.[10]Search Engine Land. Bing confirmed support for JSON-LD formatted Schema.org markup Microsoft has also said that Bing uses schema markup and, according to Search Engine Roundtable's account of a talk by Fabrice Canel of Microsoft Bing, that the markup helps its language models understand content.[11]Search Engine Roundtable. Microsoft Confirms Schema Helps Its LLMs (Copilot) Understand Your Content Copilot wasn't part of this test. That's the documented part; what we measured is that Gemini receives it. Google also asks that structured data match the visible text on the page.[12]Google Search Central. AI Features and Your Website
Schema injected by a script reaches no assistant. If your theme, an app or Google Tag Manager adds the JSON-LD after the page loads, in the test it reached none of the four. Google can read it after JavaScript rendering, but it warns that dynamically generated markup can make Shopping crawls less frequent and less reliable, right where price and availability change fastest.[9]Google Search Central. How To Add Merchant Listing Structured Data To find out where yours lives, open the product page, choose "View page source" in your browser (not the inspector, which shows the page after rendering) and search for application/ld+json. If it isn't there, a script adds it.
Nobody requested llms.txt. No assistant asked for the file during the test, and Google says you don't need to create AI text files or special markup to appear in AI Overviews or AI Mode.[12]Google Search Central. AI Features and Your Website Its optimization guide names it outright: llms.txt isn't needed for Search's generative AI features.[13]Search Engine Journal. Google's llms.txt Guidance Depends On Which Product You Ask Having one does no harm, but it doesn't replace anything above.
The meta description is still SEO. It's work for the search result, and that hasn't changed. Among the assistants, it reached only Claude through the API. Whatever you want an assistant to know about a product goes in the visible text, not in the meta description.
SEO, GEO (Generative Engine Optimization) and AEO (Answer Engine Optimization) are the same work. The same product data, for the search engine and for the assistant, delivered two ways: the markup for Google, Bing and Gemini, and the page text for all four. It's not two projects: a product page that says the same thing in the markup and in the text serves both readers at once.
How to check your store
The basics can be checked today, with no special tools and with or without Clione. The first two checks are about being found; the last three, about being read.
- The store is in all three indexes. Search
site:yourstore.comon Google, on Bing and on search.brave.com, and see whether your product pages come up. On Google, Search Console's page indexing report says which ones are indexed and why the rest are missing. - The sitemap and the robots' permissions. The XML sitemap has to be up to date and list every product page. The robots.txt mustn't block Googlebot, Bingbot or the assistants' robots, such as OAI-SearchBot, ChatGPT-User or Claude-User.
- Key facts in view. Price, availability, dimensions, materials, compatibility and the answers to the usual questions, written as text on the product page, not only in images, in the code or in tabs that load later.
- JSON-LD in the page source. In "View page source" (Ctrl+U on Windows, Cmd+Option+U on Mac) you should find application/ld+json. If you only see it in the inspector, a script or Google Tag Manager adds it, and it reaches no assistant.
- Alt text on every image that describes what the photo shows, not the file name. It reaches ChatGPT, Claude and Gemini, and Google Images uses it.
How Clione uses this
Clione writes the same product data both ways: a JSON-LD graph with the product and its FAQs, for Google, Bing and Gemini, and text on the page, the title and a visible FAQ, for ChatGPT, Claude and Perplexity. On Shopify, both halves are in the page the server sends, no scripts, through Shopify app embeds. Clione also serves an llms.txt on your store's own domain.
Clione doesn't replace your SEO agency: it doesn't do ranking strategy, link building or editorial content. It makes sure the product data is complete, well formed and where each reader looks for it, so that work reaches the assistants too.
What this study doesn't say
- That reaching an assistant means being recommended. We measured whether a fact reaches the assistant, not whether it uses it to answer or whether it changes what it recommends. The next layers of the study measure that.
- How much search and selection weigh. The index table gathers what each company documents and one outside analysis; we didn't measure it. How much of a recommendation depends on the index and on selection is for a later stage.
- Anything about the consumer apps. We measured through the APIs. The ChatGPT app, Claude.ai, the Gemini app, Copilot and Google's AI Mode may read differently, and we didn't measure them.
- Anything about visibility, traffic or sales. No figure in this table says a product page will show up more, get more visits or sell more.
- That schema is useless. JSON-LD is how Google and Bing read a product page, and Gemini receives it. What reached no assistant is the JSON-LD a script adds.
- Anything about crawlers. We measured assistants reading a page because someone asked, not any web crawler: neither the training crawlers (GPTBot, ClaudeBot, CCBot) nor the search crawlers (OAI-SearchBot, PerplexityBot, Claude-SearchBot), which are different robots. What each of them does with JavaScript is covered in the guide What an AI crawler sees in your store.
- That it's final. The results are provisional: we close the criteria once every layer is in, and if a later layer changes a figure, we correct it with a dated note in the change history.
The rest of the concepts behind how assistants read a store are laid out in the AI search reading path.
Sources
- [1] Google Search Central. Optimizing your website for generative AI features on Google Search. Accessed . ↑
- [2] Microsoft Advertising. Optimizing Your Content for Inclusion in AI Search Answers. Accessed . ↑
- [3] Profound. What Is Claude Web Search? Explained. Accessed . ↑
- [4] OpenAI. Overview of OpenAI Crawlers. Accessed . ↑
- [5] Perplexity. Perplexity Crawlers. Accessed . ↑
- [6] IndexNow. IndexNow documentation. Accessed . ↑
- [7] Google for Developers. Indexing API Quickstart. Accessed . ↑
- [8] MERJ. How Brave Search discovers new pages. Accessed . ↑
- [9] Google Search Central. How To Add Merchant Listing Structured Data. Accessed . ↑ ↑
- [10] Search Engine Land. Bing confirmed support for JSON-LD formatted Schema.org markup. Accessed . ↑
- [11] Search Engine Roundtable. Microsoft Confirms Schema Helps Its LLMs (Copilot) Understand Your Content. Accessed . ↑
- [12] Google Search Central. AI Features and Your Website. Accessed . ↑ ↑
- [13] Search Engine Journal. Google's llms.txt Guidance Depends On Which Product You Ask. Accessed . ↑
Change history
- First English version, translated from the Spanish: method and results of the study's first layer, what reaches each assistant, closed October 29, 2026.
- Added where each assistant searches and how to check a store, from our report of November 6; the table adds what Google and Bing document, and the method, the measurement dates.
Other questions
Do ChatGPT and Claude read the JSON-LD on my product page?
Does llms.txt help with AI assistants?
Is it a problem if Google Tag Manager adds my schema?
Should I stop doing structured data?
Does the meta description matter?
Related terms
JSON-LD
What JSON-LD is, what @context, @type, @id and @graph mean, why Google recommends it and how to find and check the block on your product page.
Structured data
What structured data is, which pieces make it up, what a store gets from it according to Google, and how to check it matches the product page.
llms.txt
What the llms.txt file is, what llmstxt.org proposes, what Google said in June 2026 about its effect on Search and how to check your store's.
JavaScript rendering
What JavaScript rendering is, how Google does it in a second phase, what AI bots that don't run it see and how to check it in your store.
Meta description
What a meta description is, when Google uses it as a snippet, how long it should be and how to write a different one for every product page in your store.
ChatGPT-User
What ChatGPT-User is, the agent ChatGPT uses to visit a site when a person asks it to, why robots.txt may not stop it and how to verify it.
Keep reading
Comparison
SEO vs AEO vs GEO: what changes for an online store
SEO vs AEO and GEO for an online store: what each one wins, what it asks of your product pages, how it's measured, and what Google and Bing say.
Read article →
The Corpus
Everything we learned, in one report.
A year of reading what websites tell machines, in a 100-page report plus the dataset behind it.
Request it for free →
Guide
Stop your store from blocking AI bots, Cloudflare included
If your store returns a 403, a 429 or a challenge to AI crawlers, see which layer decides it and which setting to change, from Cloudflare to robots.txt.
Read article →Make your catalog easy for bots to read
Clione fills every product page with its data in two forms: the JSON-LD graph for search engines and Gemini, a meta description for the search result, and FAQs on the page, the part every assistant reads. You review and press Push; then we check your live store so it all stays published.