Google Merchant Center Briefly Exposed Its Own AI Prompts Instead of Insights

Google Merchant Center briefly showed the actual AI prompt behind one of its insights reports, instead of the polished summary it's meant to generate. A rare, if minor, look behind the curtain at how Google's AI-generated retail insights actually work.

What was spotted

Vipul Kumar posted the find on LinkedIn: "Looks like Google Merchant Center accidentally gave me a little peek behind the curtain today... Instead of just showing the final AI-generated insight, Merchant Center was actually displaying what looked like the instructions being used to generate it."

According to Kumar's screenshot, the exposed prompt scaffolding included distinct sections for:

• What the AI was supposed to analyse. The scope of data it was told to look at
• The rules it needed to follow, constraints on tone, format or claims
• Click changes for 20 products. The specific dataset fed into that instance of the report
• How it decided which product to highlight. The selection logic behind picking one product as the headline insight
• Templates it could use for the response. Pre-built sentence structures the model fills in rather than generating freely
• The sentence it was going to generate. A preview of the model's planned output before final rendering
• A final check before showing the result. A validation step run after generation, before the insight reaches the merchant

Why it matters

This isn't a security issue or a meaningful leak of proprietary logic. It's a rendering glitch that briefly showed prompt scaffolding instead of the finished output. But it's a useful, concrete glimpse into how Merchant Center's AI-generated insights are actually built: a structured, template-constrained pipeline with an explicit selection step and a post-generation validation check, rather than a single freeform generation handed straight to the merchant. That structure explains why Merchant Center's AI insights tend to read in a fairly consistent, formulaic style. It isn't writing freely each time, it's filling in one of a fixed set of templates after running through a defined selection and rules process.

Worth keeping in mind next time a Merchant Center AI insight reads as slightly generic or templated: that's evidence of how the system is built, not a bug in a specific report.

Which report this likely is

Google's Merchant Center Help documentation for AI performance insights describes a report that tracks "performance for conversational queries with shopping intent on AI Mode and AI Overviews". Covering share of voice, competitor comparisons and product visibility across the discovery, evaluation and ready-to-buy stages of the shopping funnel. It lives under Merchant Center → Analytics → Products → AI performance, and as of Google's own documentation is limited to English-language queries in Australia, Canada, India, New Zealand and the US, a pilot, not a global feature. The "click changes for 20 products" data point and the product-highlight selection logic in Kumar's screenshot line up with the kind of per-product performance summary this report is designed to generate, though Google hasn't confirmed which specific report the exposed prompt belonged to.

That limited pilot availability is also a useful data point on its own: if you don't see an "AI performance" tab under Analytics → Products in your own Merchant Center account, and you're not in one of those five countries, that's expected. The feature hasn't reached your account yet rather than being missing or broken.

Sources

• Vipul Kumar on LinkedIn: original screenshot and spot
• About AI performance insights: Google Merchant Center Help: official documentation on scope, location and pilot availability