Blunt Findings
This is a sample report. Copperbeech is an invented store on a reserved domain that nobody can register, built to score in the sixties so the sample shows real findings. The engine, the scoring and the checks are the ones a paying customer gets. Speed is not measured here because the store does not exist, and the report says so rather than scoring it zero.
Download the PDF
Blunt Findings

AI Shopping Readiness Audit

Store copperbeech.examplePlatform Shopify Catalogue 18 productsRead on 09 September 2026Order bf_sample0001
69 / 100
Needs work

When a shopper asks an AI assistant for what this store sells, this is how far the assistant gets: whether it can read the products, confirm price and stock, trust the store and reach it.

Scored on 90 of 100 available points. Not measured: Speed.

SectionPointsScore
Catalogue readability15.9 / 2564%
Structured data20.3 / 2581%
Agent access11.0 / 1573%
Trust and policy12.3 / 1582%
Speednot measured
Visibility spot check2.5 / 1025%
Section scores
Section scores as a share of their points.

Findings

high 1 page of 15 sampled have no Product structured data in the served page
Add Product JSON-LD to the product template (most themes have it; some apps remove it). It is the single fact sheet every agent reads first.
high 2 AI search or shopping crawlers are blocked from product pages
In robots.txt (Shopify admin, Online Store, Themes, Edit code, robots.txt.liquid) allow these agents on /products/ and /collections/. Blocking a training crawler is a separate choice and can stay.
medium 61% of titles do not name the product type
A shopper asks an agent for "trainers" or "a wool jumper", so the title should say which it is: brand, product type, then the one or two attributes they would ask for, then size or variant. If titles must stay short for the brand, make sure the product type field and the first line of the description say it plainly; agents read both.
medium 61% of titles are under 20 characters, numbered, or led by marketing words
Shopify admin, Products, edit each title. Start with the best sellers.
medium 56% of descriptions are under 50 words
Give every product a description that states material, dimensions, weight, compatibility and care in plain sentences. Agents extract facts; they cannot infer them from a photo.
medium 56% of descriptions contain no measurable specification
Add a short specification list (a bulleted list in the description) with units: size, weight, capacity, material, what is in the box.
medium 9 pages of 15 have no GTIN in structured data
Add the barcode to each variant in Shopify admin and make sure the theme outputs it as gtin. A GTIN is how an agent matches your listing to the same product everywhere else and to reviews of it.
medium Shipping policy is disallowed for crawlers in robots.txt
Shopify hides /policies/ from every crawler by default, so an agent that honours robots.txt cannot read it. Publish the same text on a normal page (for example /pages/shipping) and link it from the footer, or allow /policies/ in robots.txt.liquid.
medium Returns and refunds is disallowed for crawlers in robots.txt
Shopify hides /policies/ from every crawler by default, so an agent that honours robots.txt cannot read it. Publish the same text on a normal page (for example /pages/returns) and link it from the footer, or allow /policies/ in robots.txt.liquid.
medium Contact page is disallowed for crawlers in robots.txt
Shopify hides /policies/ from every crawler by default, so an agent that honours robots.txt cannot read it. Publish the same text on a normal page (for example /pages/contact) and link it from the footer, or allow /policies/ in robots.txt.liquid.
low No llms.txt
Publish /llms.txt: a short plain-text page naming the store, what it sells, its policies and where the catalogue is. Cheap, and the agents that read it read it first.

Review

Overall Summary

What AI Agents Can Read

Section scores as a share of their available points
Section scores as a share of their available points

Whether They Can Trust the Store

Whether They Can Reach It

The Fix List

30-Day Plan

Week 1. Edit robots.txt.liquid: remove the OAI-SearchBot and PerplexityBot blocks and allow the policies folder. Check afterwards that a policy page loads for a crawler. Add shipping, returns and contact links to the homepage footer. Publish llms.txt.

Week 2. Fix the ten titles that do not name the product type, using facts already in each product. Add the barcode to the 9 products missing a GTIN, highest-priced first. Add Product structured data to camp-mug.

Week 3. Write the specification block for the ten thin descriptions, following the pattern your own lambswool jumper already sets: weight, material, measurements, care. Add alt text to those products' images while you are in each one.

Week 4. Re-run the queries you lost and see whether anything has changed. Add a short FAQ page answering what you get asked most, since that is the page assistants quote from when a shopper asks a question you have already answered.

1. Catalogue readability

All 18 products were read from the public catalogue. Titles, descriptions, vendor, type, images and variants were measured mechanically.

CheckMeasuredPoints
Titles name the product type38.9%1.6 / 4
Titles 20+ characters, no numbering, no marketing words38.9%1.6 / 4
Descriptions of 50 words or more44.4%1.8 / 4
Descriptions containing specifications44.4%1.3 / 3
Vendor (brand) filled100.0%2.0 / 2
Product type filled100.0%2.0 / 2
Product type casing consistentyes1 / 1
Images per product (target 3+)4.281.5 / 1.5
Images with alt text74.0%1.1 / 1.5
Variants with a SKU100.0%2.0 / 2
Catalogue checks
Share of products passing each catalogue check.

2. Structured data

15 product pages were read, spaced evenly through the catalogue, and their Product structured data checked property by property.

CheckMeasuredPoints
Product structured data present93.3% of 15 pages7.5 / 8
Offer with price, currency and availability93.3%5.6 / 6
Brand in structured data93.3%1.9 / 2
SKU or MPN in structured data93.3%1.9 / 2
GTIN (barcode) in structured data40.0%1.6 / 4
Rating in structured data46.7%0.9 / 2
Image and description in structured data93.3% / 93.3%0.9 / 1
PageProduct dataOfferBrandSKUGTINRatingReviews app
/products/british-lambswool-rollneck-jumper-oatyescompleteyesyesyesyes
/products/british-lambswool-rollneck-jumper-slateyescompleteyesyesyesyes
/products/waxed-cotton-field-jacket-oliveyescompleteyesyesyesyes
/products/waxed-cotton-field-jacket-navyyescompleteyesyesyesno
/products/harris-tweed-overshirt-heatheryescompleteyesyesyesyes
/products/selvedge-denim-work-trouser-indigoyescompleteyesyesyesyes
/products/oiled-leather-belt-tanyescompleteyesyesnono
/products/the-daily-teeyescompleteyesyesnono
/products/the-daily-tee-blackyescompleteyesyesnono
/products/weekenderyescompleteyesyesnono
/products/study-shirt-ecruyescompleteyesyesnoyes
/products/study-shirt-indigoyescompleteyesyesnono
/products/camp-mugnononononono
/products/wool-throw-charcoalyescompleteyesyesnono
/products/walking-scarf-mossyescompleteyesyesnoyes

3. Agent access

CheckMeasuredPoints
robots.txt presentyes1 / 1
AI search and shopping crawlers allowed on product pages6 of 86.0 / 8
llms.txt presentno0 / 2
Sitemap presentyes2 / 2
Products covered by the sitemap100.0%2.0 / 2
CrawlerUsed forKindProduct pagesNamed in robots.txt
OAI-SearchBotChatGPT search and shoppingsearchblockedyes
ChatGPT-UserChatGPT, when a user asks it to open a pagesearchallowedno
GPTBotOpenAI model trainingtrainingblockedyes
Claude-UserClaude, when a user asks it to open a pagesearchallowedno
Claude-SearchBotClaude searchsearchallowedno
ClaudeBotAnthropic model trainingtrainingblockedyes
PerplexityBotPerplexity searchsearchblockedyes
Perplexity-UserPerplexity, when a user asks it to open a pagesearchallowedno
GooglebotGoogle Search and Shoppingsearchallowedno
Google-ExtendedGemini model trainingtrainingallowedno
AmazonbotAmazon and Alexasearchallowedno
BytespiderByteDance model trainingtrainingallowedno
CCBotCommon Crawl, used for many training setstrainingblockedyes
Applebot-ExtendedApple Intelligence trainingtrainingallowedno
meta-externalagentMeta AI trainingtrainingallowedno

Sitemap: found, 18 product URLs. llms.txt: not found.

4. Trust and policy

CheckMeasuredPoints
Shipping policy page, with concrete times or costsfound, concrete3 / 3
Returns policy page, with a concrete windowfound, concrete3 / 3
Policy pages readable by crawlers (not disallowed in robots.txt)1 of 60.3 / 2
Contact page with an email, phone or formfound, with details3 / 3
About pagefound1 / 1
Privacy policyfound1 / 1
Terms of servicefound1 / 1
Shipping, returns and contact linked from the homepage0 of 30.0 / 1
PageFound atWordsConcreteCrawlers allowedLinked from home
Shipping policy/policies/shipping-policy52yesnono
Returns and refunds/policies/refund-policy43yesnono
Contact page/policies/contact-information79yesnono
About page/pages/about31yesyes
FAQnot found
Privacy policy/policies/privacy-policy95noyes
Terms of service/policies/terms-of-service90noyes

5. Speed

Not measured on this run.

Mobile, measured by PageSpeed Insights on the day of the audit.

6. Visibility spot check

CheckMeasuredPoints
Store appeared in buyer-style queries2 of 82.5 / 10

Eight searches a shopper might make, run once each through web search on 2026-09-09, UK market. AI shopping assistants draw on the same index. A spot check on one day, not a share or a ranking.

SearchKindStore appearedWho appeared
best british lambswool jumper for winter ukpurchasenonorthfell.example, moorandpike.example, thewoolrooms.example, brackenmills.example
waxed cotton jacket under 300 pounds ukpurchasenomoorandpike.example, staveley-co.example, brackenmills.example, oldforge.example
waxed cotton vs oilskin jacket for wet weathercomparisonnooutdoorjournal.example, northfell.example, staveley-co.example
which jumper is warmer lambswool or merinocomparisonnothewoolrooms.example, fibrefacts.example, northfell.example
380gsm lambswool rollneck jumper british madespecyesnorthfell.example, thewoolrooms.example
harris tweed overshirt mens ukspecnoharristweedshop.example, staveley-co.example, oldforge.example, brackenmills.example
Copperbeech knitwear reviewbrandyesbrackenmills.example
clothing made in britain from british wooldifferentiatornomadeinbritain.example, thewoolrooms.example, northfell.example, moorandpike.example

Method