The advice about getting cited by AI gets repeated far more often than it gets tested.
See which AEO claims survive the data
Hey, I'm Maryam. Twice a month, I take one claim people keep repeating about AI search and test it against hundreds of real citations. You get the result and the full dataset.
One email per experiment. No spam, unsubscribe anytime.
Why Seemily Exists
Everyone wants to know what gets content cited by AI. Visibility tools can show you where you’re cited. Seemily tests what might explain it, one claim at a time, and publishes what it finds.
The hard part is the engines themselves. Ask Perplexity the same question twice and you can get two different sets of sources. So a before-and-after on one or two articles can’t tell you whether your change worked or the engine just gave a different answer that day.
So I don’t test one article. My AEO experiments log citations across many queries, apply a grading rule I write down before I see any data, and publish the full set behind every result, including the ones where nothing happened.
I’ve spent six years getting articles to rank and making sure they converted once they did. What I can’t tell you anymore is how much of that survives when AI answers the question outright and the reader never reaches a results page. So I’m finding out in public, and posting what I find either way.
How I Test Claims
Every experiment here clears these four checks before I publish it.
01
Large samples, with minimum
Every hypothesis runs against real AI citations from many different queries and every test has a minimum sample set in advance. Below it, the result doesn’t get graded, because one unusual result can swing the whole number.
02
The rule gets written before the data comes in
I define exactly what counts as a hit before I log a single result, and that definition doesn’t move once I see which way the numbers are going.
03
Two approaches, thresholds set in advance
Every test uses one of two approaches: a pattern scan, which compares groups of citations, or an overlap test, which checks whether two sets of results match.
04
Nulls get published too
When there’s no gap between groups, that gets written up exactly like a win too. A result that finds nothing still answers the question.
If a claim on this site doesn’t meet all four, it doesn’t go up.
Where To Start
Two streams I keep apart on purpose.
The Lab
Every hypothesis in full. What I tested, how many citations it ran against, the rule I set before I looked, and the grade it came back with. The tests that found nothing are published with the same weight as the ones that worked.
Field Notes
Faster, looser, and openly opinionated. Something odd in my Search Console data. A claim another practitioner made that deserves a second look. A guess I haven’t tested yet, and my observations. Some of it ends up in the Lab.
Guides
Longer pieces on SEO, AEO, and GEO, written from work I’ve done.
Get the Next Result Before Anyone Else
Twice a month I take one AEO claim and test it against a real sample of citations. You get the result and the dataset, straight to your inbox.
One email per experiment. No spam, unsubscribe anytime.