What a person sees: the headline "Your next customer is not a person." AI shopping agents choose products from structured data, not from your homepage design. Most stores are invisible to them. Scan yours and find out in twenty seconds.
What an agent reads, as this page's WebPage structured data: name "Sextant - Agent readiness for your store.", description "Sextant scores any ecommerce store on the 30 signals AI shopping agents use to find, understand and recommend products. Free scan, no signup.", in en, part of the Sextant website.
Not included in that data: primaryImageOfPage (absent - an agent cannot cite what this page looks like); dateModified (absent - freshness cannot be verified); speakable (absent - no voice-assistant reading hint).
Readiness score
- Discovery35
- Crawl access88
- Product schema58
- Merchant data47
- Content quality70
- Failllms.txt published and describes this store
- PassGPTBot is allowed
- FailGTIN or MPN populated
- WarningShipping terms are machine readable
Scan your store- free, no signup
The problem
Nothing breaks. You just stop being an option.
There is no error page for this. A store can trade normally for a year while being unreadable to every agent that would have recommended it.
A single line locks the door
Crawler blocks get added during a scraping scare, or arrive as a plugin default, and then nobody revisits them. We check five AI crawlers by name against your real rules, at the site root and on an actual product path.
User-agent: *Disallow: /cartUser-agent: GPTBotDisallow: /User-agent: ClaudeBotAllow: /
One line, added by a plugin default years ago, removes the store from every OpenAI surface. Nobody notices, because nothing breaks.
Valid schema is not useful schema
Most stores that have structured data have it in name only: a Product node with an empty SKU, no GTIN and one image. It validates. It cannot be matched against the same product anywhere else, which is the entire job.
"@type": "Product","name": "Harbour Shell Jacket","offers": { "price": "289.00" },"sku": "","gtin13": missing,"aggregateRating": missing,"image": [ 1 of 6 ]
A validator passes this. An agent trying to decide whether your jacket is the same jacket it found on three other sites cannot.
Same page. Two readers.
Nothing is exaggerated: this is one product page from the demo store, next to what an agent actually receives from it. One view is how it renders, the other is what it serves.
Harbour Shell Jacket
4.8(127 reviews)
$289.00
In stock, ships today
A three-layer waterproof shell cut for coastal weather: 20k/20k rated fabric, fully taped seams, and a two-way front zip under a storm flap. The hood adjusts with one hand and stows flat when the rain stops.
Pit zips run long for fast venting, the hem cinches over a mid layer, and both hand pockets sit above pack-strap height. Weighs 410 g in a men's medium. Cut is regular; size up for winter layers.
JSON-LD, as served
{
"@context": "https://schema.org",
"@type": "Product",
"name": "Harbour Shell Jacket",
"sku": "",
"image": "cdn/img/hs-1.jpg",
"description": "A great addition to
your daily wardrobe.",
"offers": {
"@type": "Offer",
"price": "289.00",
"priceCurrency": "USD"
}
}Extracted text
A great addition to your daily wardrobe.- 40 characters
Not in the payload
- Fail
sku: empty string - Fail
gtin13: absent - Fail
aggregateRating: absent - Fail
availability: absent - Warning
image: 1 of 6
What a person sees at northline.example/products/harbour-shell: Harbour Shell Jacket, $289.00, rated 4.8 from 127 reviews, in stock, ships today, sizes XS, S, M, L, XL available. A three-layer waterproof shell cut for coastal weather: 20k/20k rated fabric, fully taped seams, and a two-way front zip under a storm flap. The hood adjusts with one hand and stows flat when the rain stops. Pit zips run long for fast venting, the hem cinches over a mid layer, and both hand pockets sit above pack-strap height. Weighs 410 g in a men's medium. Cut is regular; size up for winter layers.
What an agent gets, as the JSON-LD actually served: { "@context": "https://schema.org", "@type": "Product", "name": "Harbour Shell Jacket", "sku": "", "image": "cdn/img/hs-1.jpg", "description": "A great addition to your daily wardrobe.", "offers": { "@type": "Offer", "price": "289.00", "priceCurrency": "USD" } }
The text extracted from that same payload instead of the page copy: "A great addition to your daily wardrobe." - 40 characters.
Not in the payload: sku (empty string); gtin13 (absent); aggregateRating (absent); availability (absent); image (1 of 6).
An agent reading this page cannot say which jacket this is, whether it is in stock, or whether anyone has ever rated it. The person can see all three without trying.
Readiness score
A sample report for a fictional store. Yours takes about twenty seconds.
- Discovery35
- Crawl access88
- Product schema58
- Merchant data47
- Content quality70
- Failllms.txt published and describes this store
- PassGPTBot is allowed
- FailGTIN or MPN populated
- WarningShipping terms are machine readable
- PassOrganization schema on the homepage
- FailDescriptions at least 500 characters
The report
30 checks. Every failure ships with its fix.
Five categories, weighted by what actually blocks a sale. Crawl access and product schema carry the most because they are gating: if a crawler cannot get in, or a page has no structured data, nothing else can be seen.
- 01Discovery
- Can an agent find the machine readable entry points to your store.
- 02Crawl access
- Are AI crawlers allowed in, over a fast and secure connection.
- 03Product schema
- Is each product described in structured data an agent can trust.
- 04Merchant data
- Are returns, shipping and business identity resolvable without a human.
- 05Content quality
- Is there enough substance for an agent to compare and recommend you.
The fix path
From invisible to recommended
The scan is free and complete. Nothing is held back to force a sales call.
Scan
Paste your URL. 30 checks in about twenty seconds, no signup, nothing installed.
Report
A score, a grade, and every failing check with the evidence we found and the fix written out.
Fix
Implement it yourself from the report, or have us do the whole list for a fixed fee.
Visible
Agents can find, read, compare and recommend you. Rescan any time to prove it stuck.
Done for you
Fixed price$400 flat
We implement every fix our access allows and rescan to show you exactly what moved.
- Everything in the free scan
- llms.txt, llms-full.txt, agents.md and a UCP manifest, written from your real catalog
- Product and Organization schema implemented directly in your theme
- robots.txt opened to AI crawlers
- Rescan and a written handover
On WooCommerce, custom stacks and Shopify, we deploy llms.txt, llms-full.txt and agents.md at your store's own root - on Shopify via a theme template we install with the access we already request. The UCP manifest is the one exception: Shopify exposes no override for /.well-known/ucp on any theme or account, so there we hand you the hosted URL directly, or deploy it at your root if Cloudflare fronts your domain.
Book it - $400Full tiers and questions on the pricing page.
Measured, not promised.
40
checks per scan
5
weighted categories
Live
crawl every time, nothing cached
Questions
Before you scan
- What does 'agent readiness' mean?
- Whether an AI shopping agent can find your store, read your products as structured data rather than prose, and trust your returns and shipping terms enough to recommend you. It is not a score you can talk your way into. Either the crawler is let in and the schema is there, or it is not.
- What does the scan actually check?
- 30 checks across five categories: discovery files such as llms.txt and agents.md, whether AI crawlers are allowed in by robots.txt, product structured data, machine readable returns and shipping, and content depth. Every check comes back with the evidence we found and the fix, not just a number.
- Does the scan change anything on my store?
- No. It only reads what is already public: your homepage, robots.txt, sitemap, a sample of product pages and your policy pages. Nothing is installed, no account is created, and nothing on your store is written to.
- What does it cost to fix what the scan finds?
- The scan and its fixes are free to read and free to implement yourself. If you would rather we did it, done for you implementation is $400 flat for Shopify and WooCommerce stores up to 50 products. Larger catalogs and other platforms quoted before we start. You can book and pay for it in one step, no account needed.
- What if my store is bigger than 50 products?
- Then it is quoted rather than flat, and the quote is fixed and agreed before any work starts. Tell us the platform and roughly how many products you have and we will price it. If you have already booked at $400 and the store turns out to be over scope, we agree the difference with you or refund you in full, before we touch anything.
- How long does a scan take?
- Usually 15 to 30 seconds. We fetch your homepage, six discovery files, your sitemap and up to 5 product pages, three requests in flight at a time so we are not hammering your server.
Writing
More on what agents actually read
Essays and practical guides, if the report above raised a question this page did not answer.
Free scan
Find out where you stand
One URL, twenty seconds, the whole report. Free, no signup, and shareable with whoever maintains your store.
Scan your storeDone for you
Have us fix it
$400 flat for Shopify and WooCommerce stores up to 50 products. Larger catalogs and other platforms quoted before we start. We implement every failing check we can, rescan, and hand it back in writing.
Get it fixed