Run free scan
Menu
method

Eleven checks. Every weight published.

75 points for the five AI checks, 25 for the six search basics. Every grade is a fact about your store on the day of the scan. Same captured inputs, same method, same result, so two runs can be set side by side.

How a score is worked out

Goodfull points
Needs workhalf
Brokennone
Inconclusiveleft out, the rest scaled to 100
0 to 44
Hard to read
45 to 69
Partly readable
70 to 100
Readable

Compare your score only with your own earlier scores. It is not a ranking against other shops, and it does not predict whether an assistant will mention you.

AI checks

5 checks · 75 points
26pts
Can AI assistants reach your shop at all?
Check name: AI assistant access

Whether the automated visitors that read your site for AI tools are let in, or turned away by your host, your security plugin or anything in between without telling you. Nothing else matters if this one fails.

19pts
Can software read your product details?
Check name: Product details

Whether price, stock, sizes and product codes are written on your product pages in a form software can read, and whether they match what a shopper sees.

13pts
Have you told them what your shop sells?
Check name: Shop summary (llms.txt)

Whether your shop has a small llms.txt file that says in plain words what you sell, how it is grouped, and what your policies are. It saves an assistant from guessing its way around your pages.

9pts
Do your pages answer what shoppers ask?
Check name: Answers on the page

Whether your product and category pages state materials, sizing, delivery and returns in words rather than inside a picture.

8pts
Does the page load in time?
Check name: Page speed

Whether your page arrives quickly, and shows its detail without waiting on code that these automated visitors do not run.

Search basics

6 checks · 25 points
5pts
Does every page have a title and a description?
Check name: Titles and descriptions

Whether each page says what it is, once, in the short title and summary that search engines and assistants read first.

5pts
Is your list of pages up to date?
Check name: Page list (sitemap.xml)

Whether your shop has a sitemap.xml, the file that lists all your pages, whether robots.txt points to it, and whether it matches the products you sell today.

5pts
Is the whole shop on a secure address?
Check name: Secure address

Whether your security certificate is valid, every page uses the secure https address, and the older addresses jump straight there in one step.

4pts
Does each product have one main web address?
Check name: One main web address

Whether the different versions of a page, the ones with sizes, filters or tracking tags in the address, all point back to one main address. Otherwise one product can be read as five.

3pts
Is there one clear heading on each page?
Check name: Headings

Whether each page has one main heading that names what is on it, with smaller headings in order underneath.

3pts
Do your images describe themselves?
Check name: Image descriptions

Whether every image that means something carries a short written description. It helps shoppers using a screen reader first, and software second.

The points are fixed and published here. They follow what stops an assistant first, not what is easiest to sell. We check that the search basics are in place. We do not track keywords, positions or rankings, and we never report on them.

An Inconclusive check never counts against you.We take it out of the sum and scale the other points back up to 100, so a short outage cannot make your store look worse than it is. The report always names the checks we left out.

A worked example

The same sums the scanner does. You can check them with a calculator.

CheckWeightGradePoints
AI assistant access26Needs work13.0
Product details19Broken0.0
Shop summary13Broken0.0
Answers on the page9Needs work4.5
Page speed8Good8.0
Titles and descriptions5Needs work2.5
One main web address4Good4.0
Headings3Broken0.0
Image descriptions3Needs work1.5
Page list (sitemap.xml)5Good5.0
Secure address5Good5.0

Step 1. Add the AI-check points: 13.0 + 0.0 + 0.0 + 4.5 + 8.0 = 25.5 of 75

Step 2. Add the search-basics points: 2.5 + 4.0 + 0.0 + 1.5 + 5.0 + 5.0 = 18.0 of 25

Step 3. All eleven checks gave a result, so the points counted add up to 100: 25.5 + 18.0 = 43.5, which rounds to 44, hard to read

If one check comes back Inconclusive.Say page speed gave nothing back. Its 8 points drop out of the sum: 35.5 points earned out of 92 counted, so 35.5 ÷ 92 × 100 = 39. The report names the check we left out, so the two scores are never quietly compared.

What a score can and cannot say

Every report sorts its evidence into the same three layers, so it is always clear which part is measured and which part is not claimed at all.

Layer 1

Technical facts

What the checks measured on your public pages on the day of the scan. These are facts about your store, they are the only thing we will ever promise to do, and you can measure them again yourself.

Layer 2

Observed visibility

What assistants actually said when we asked them, on the dates given. That is a dated observation with a written method behind it, not a forecast, and it is not promised to repeat.

Layer 3

Business outcome

Not promised. Nothing here predicts rankings, mentions, visits or sales, and no number in a report should be read as a promise of any of those.

the limits

What we will never claim

Neverthat a score of 100 means an assistant will mention you. It means nothing we can measure is stopping it.
Neverthat we know how any assistant chooses which products to name. Nobody outside those companies does.
Alwaysthat every finding is something you can check yourself. If you cannot repeat one, tell us, and we will take the check out.
Alwaysthis method page is the record of the current checks and weights, and changes are published on this page.

What we do not measure

Keyword rankings, traffic, or whether any assistant mentions you. Nobody can measure that honestly, so we do not report on it.

See these checks run on your store

Every finding in your report shows the points it carries and the grade it earned, so you can add them up yourself.

Store address only. No email, no card.

Method changes

2026.09 (6 September 2026)

Monitoring comparisons restart at a method change.

  • Assistant access is graded on sampled public URLs.
  • Training crawlers (GPTBot, ClaudeBot, Google-Extended) are reported on their own unscored line; the access check scores the six search and user-fetch crawlers. Google-Extended also controls Gemini grounding; it does not affect Google Search inclusion or ranking.
  • Product prices need a currency. A Product record without a name now fails.
  • The sitemap check passes when any of /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml or a robots.txt Sitemap directive parses.
  • Duplicate-record and non-standard-wrapper warnings count toward the product details credit.
  • FAQ page data needs at least one question with an answer.
  • Product discovery works across store platforms; product pages nested up to three levels deep and Shopify ProductGroup records are recognised.
  • One linked help or FAQ page is sampled.

2026.08 (published weights, first version)