We tracked 1,885 pages adding schemas. AI quotes barely moved.

AI-cited pages were almost three times more likely to have JSON-LD than uncited pages.

This is a big gap and the kind of statistic that gets shared in LinkedIn carousels and conference slides as proof that schemas are a lever for AI visibility.

But we were not satisfied with the data as it could well be a connection and not a cause.

Schema markup is typically used on better-maintained, more sophisticated websites, and these same websites publish stronger content, build more authority, earn more links, and do all the other things that get pages cited.

Scheme could do real work, but it could also just ride the wave of every other signal.

Therefore, we couldn’t really answer the question that SEOs really care about: If I add schema to my page, will I be cited more by AI?

To find out, we conducted a second study to isolate the effects of adding schemas.

Here’s what we found.

We tracked 1,885 web pages that added the JSON-LD schema between August 2025 and March 2026, matched them against 4,000 control pages, and measured citation changes in Google AI Overviews, AI Mode, and ChatGPT.

Adding the schema did not result in a major increase in citations on any platform.

These percentages come from our most reliable analysis (a matching difference-in-differences [DiD] check).

In this test, both AI mode and ChatGPT-treated pages performed slightly better on average than control pages, but the differences are so small that they could easily be random noise across thousands of URLs.

AI overviews showed a decrease of 4.6%, which is small but statistically significant compared to matched control sites.

But that’s not quite the whole story – we’ll get into that in the next section.

So overall, we can’t say whether the scheme has done some good or nothing at all.

AI summary citations on treated pages decreased by 4.6% compared to control pages, and the result is “statistically significant” (the chance of such a large gap occurring purely by chance is about 1 in 2,500).

But before anyone reads this as “adding a schema will hurt your AI overview citations,” you need to consider two things.

1. The absolute size is small. We’re talking about an average loss of about 12 daily citations per page, in a sample where most pages received hundreds.
2. Both the treated and matched control sites were already on a steep downward trend before Schema has been added – the kind of decline you would expect if AI Overviews moves away from these specific types of content for reasons unrelated to schema (e.g. a Google update that changes what is displayed, the content is out of date, or Google hasn’t recrawled the page recently).

That is, if adding schema had no effect on citations in any way, we would expect treated pages and matched controls to decline to the same extent (which is broadly what we see for AI Mode and ChatGPT).

The fact that treated pages declined slightly more suggests that the scheme had a small negative effect – but it could also reflect other factors.

Based on this data alone, we cannot say which one it is.

Using Brand Radar, Xibeijia identified several million URLs cited in AI overviews.

She then pulled the HTML history from our crawler database and labeled whether each URL contained the following , and spotted the date that schema presence transitioned from “False” to “True”.

This left her with 1,885 pages that introduced JSON-LD between August 2025 and March 2026.

Finally, to analyze all of that data, she used Agent A, our new AI marketing agent.

For each page Xibieijia knew two key dates:

• The last day our crawler checked the page and found no JSON-LD
• The first day our crawler detected JSON-LD on the page

The day a page added JSON-LD is its treatment date.

Xibeijia measured how many times each page was cited by Google AIO, Google AI Mode, and ChatGPT in the 30 days before and 30 days after the treatment date.

The tricky part of any study like this is seeing past noisy data.

Citations across all of AI search were moving during this period; AI Overviews were contracting, AI Mode was exploding.

If Xibeija had just done a simple before-and-after comparison, it would have been measuring the platform trend, not the schema effect.

So for each treated URL she picked 3 control URLs (from different domains, with similar pre-period citation levels) that had never added JSON-LD.

Comparing two groups of pages that were getting cited at the same rate before—where the only main difference was that one group added schema—made it easier to isolate what schema actually did.

We looked at the data four different ways to make sure any conclusion held up under scrutiny.

In each test, we asked a slightly different version of the question: “did schema do anything?”

You only really believe a finding when several of them agree and, in this case, they do.

Test 1: Compared average citation changes between treated and control pages (a two-sample t-test).

Test 2: Ran a difference-in-differences (DiD) analysis to strip out platform-wide trends. This is the test we trust most, and the source of the findings in this article.

Test 3: Plotted citations week-by-week to check whether treated and control pages were already drifting apart before schema was added (an event study).

Test 4: Re-ran the difference-in-differences (DiD) with a symmetrical window that excluded the recrawling period, to make sure the result wasn’t sensitive to how we defined “before” and “after.”

All four tests told the same story: no citation growth in AI Mode, no citation growth in ChatGPT, and a small AI Overview decline that’s real but small enough that we can’t definitively pin it on schema.

The most consistent finding is that not much really changed—schema had no clear positive or negative effect.

Want to know whether schema works for your site specifically? Run a smaller version of this study yourself. Brand Radar can help when it comes to tracking the course of AI citations:

• Pick 5–10 test pages where you plan to add JSON-LD. Ideally pages already getting some AI citations, so you have a baseline (pages with zero citations make it harder to tell whether schema did nothing, or whether the page just wasn’t going to get cited either way). You can check this in the Cited Pages report.

• Pick 5–10 control pages with similar citation levels that you’re not adding schema to. This is what separates “schema did something” from “AI Overviews shifted for everyone that month.”
• Record baseline citations for both groups across AI Overview, AI Mode, and ChatGPT in Brand Radar. Just apply URL filters to isolate those citation numbers.

• Add schema to your test pages and note the date. Don’t change anything else on those pages during the test window.
• Compare both groups after 30 days (or longer if you can). The question is: “did treated pages go up more than control pages did?”

If both groups moved by similar amounts, that’s more to do with the platform trend than the schema.

But if treated pages outperformed controls, that’s a sign schema is having a positive impact on citations.

If you run this on your own pages and get a different result to ours, let us know.

For pages already getting cited by AI, adding JSON-LD schema didn’t boost citations on Google AI Mode or ChatGPT, and showed only a small decline in AI Overviews that we can’t clearly attribute to schema.

So why are 53% of AI-cited pages running schema?

Because the sites that add structured data tend to also invest in technical SEO, publish authoritative content, build links, maintain their pages, and rank well in regular search.

AI systems are more likely to retrieve this kind of content, so cited pages over-index on all of those signals at once. Strip schema out and it’s very likely the rest of the signals still carry the page through to citation.

If you’re already doing the rest of the SEO work well, JSON-LD isn’t going to be the unlock.

There are still, of course, many good reasons to use JSON-LD schema (rich results, voice assistants, knowledge graphs, downstream entity recognition).

But if the only reason you’re adding it is to get more AI citations on pages that are already visible, our data doesn’t support that bet.