Example test
The questions come from the published standard, not from us guessing what matters. AisleLens Coffee Standard v1.3 v1.3 carries 42 entries; 10 of them both are executable against a public product page and apply to this product. The applicability rules were written before this test ran and are published beside the standard.
No executable entry was excluded — all 10 applied to this product, and all 10 were asked.
Read from: product copy, structured data, product title, variant options, page description. Not publicly inspectable: product metafields.
Four states, and only one of them is a claim about the product. The distinction between “we could not read this” and “you do not publish this” is the difference between a finding and an accusation, and only one of them is ever true.
pass_evidencednot_provenProven
ALS-COFFEE-1.3-FORMAT-001 · Whole bean option is listed and purchasable
A "Whole Bean" variant is listed and purchasable.
Read from variant options at https://klatchcoffee.com/products/ethiopia-yirgacheffe-supernatural
Audited: this row was read individually in the v3.2 coffee measurement and adjudicated true pass — "Whole Bean" heads an explicit grind list separate from the size option.
Surfaces checked: variant options
Not proven
ALS-COFFEE-1.3-FORMAT-002 · Ground option is listed and purchasable
Checked the public variant list, and no "Ground" variant is offered on this product.
Taken from the standard entry, published before this test ran. The bar was not set after seeing the answer.
Surfaces checked: variant options
Proven
ALS-COFFEE-1.3-GRIND-001 · Espresso grind option is listed and purchasable
A "Espresso" variant is listed and purchasable.
Read from variant options at https://klatchcoffee.com/products/ethiopia-yirgacheffe-supernatural
Audited: this row was read individually in the v3.2 coffee measurement and adjudicated true pass — "Fine (Espresso)" names an espresso grind size directly.
Surfaces checked: variant options
Proven
ALS-COFFEE-1.3-GRIND-002 · Filter grind option is listed and purchasable
A "Filter" variant is listed and purchasable.
Read from variant options at https://klatchcoffee.com/products/ethiopia-yirgacheffe-supernatural
Audited: this row was read individually in the v3.2 coffee measurement and adjudicated true pass — "Medium Coarse (Chemex / Cone Filter)" is a filter grind size; "Medium (Pour Over / Auto Drip)" corroborates.
Surfaces checked: variant options
Proven
ALS-COFFEE-1.3-WEIGHT-001 · A weight or measurement is stated in readable text
Stated in your variant options.
2 lb bag.
Read from variant options at https://klatchcoffee.com/products/ethiopia-yirgacheffe-supernatural
Audited: this row was read individually in the v3.2 coffee measurement and adjudicated true pass — The quoted variant option "2 lb bag." is one of the product's own sizes (alongside 310 g and 5 lb).
Surfaces checked: product copy, structured data, product title, variant options, page description
Not proven
ALS-COFFEE-1.3-CERT-001 · An organic claim is stated in readable text
Checked product copy, structured data, product title, variant options and page description, and none of them state an organic claim in wording an AI buyer could verify.
Taken from the standard entry, published before this test ran. The bar was not set after seeing the answer.
Surfaces checked: product copy, structured data, product title, variant options, page description
Not proven
ALS-COFFEE-1.3-CERT-002 · A fair-trade scheme claim is stated in readable text
Checked product copy, structured data, product title, variant options and page description, and none of them state a fair trade claim in wording an AI buyer could verify.
Taken from the standard entry, published before this test ran. The bar was not set after seeing the answer.
Surfaces checked: product copy, structured data, product title, variant options, page description
Not proven
ALS-COFFEE-1.3-SOURCE-001 · A single-origin claim is stated in readable text
Checked product copy, structured data, product title, variant options and page description, and none of them state a single origin claim in wording an AI buyer could verify.
Taken from the standard entry, published before this test ran. The bar was not set after seeing the answer.
Surfaces checked: product copy, structured data, product title, variant options, page description
Not proven
ALS-COFFEE-1.3-IDENT-001 · A product identifier is published in structured data
Your product structured data publishes no GTIN or MPN, so a machine buyer can't match this product to a catalogue entry.
Taken from the standard entry, published before this test ran. The bar was not set after seeing the answer.
Surfaces checked: structured data
Proven
ALS-COFFEE-1.3-DELIV-001 · A dispatch or delivery window is stated
Delivery timing is stated in your shipping policy.
Domestic Shipping Policy Shipment processing time All orders are processed within 2-3 business days - please keep in mind that we do fresh-roast all coffee prior to shipment after you order, and that orders are not processed, shipped or delivered on weekends or holidays.
The result page shows this cut to 180 characters (Domestic Shipping Policy Shipment processing time All orders are processed within 2-3 business days - please keep in mind that we do fresh-roast all coffee prior to shipment after…). The whole sentence is above — a receipt a merchant cannot read in full is not a receipt.
Read from shipping policy at https://www.klatchcoffee.com/policies/shipping-policy
Audited: this row was read individually in the v3.2 coffee measurement and adjudicated true pass — "All orders are processed within 2-3 business days" states a real dispatch window, with the weekend/holiday caveat attached.
Surfaces checked: product copy, structured data, product title, variant options, page description. The evidence came from shipping policy, which is fetched separately from the product page and so does not appear in that list.
Published, because a test result you cannot calibrate is a number without a unit. AisleLens Coffee Standard v1.3 v1.3 was executed against 100 real coffee products across 77 storefronts, and every one of the 160 requirements it reported as proven was read individually against the store's full page text. 7 of those passes were wrong.
Read that bound carefully. It is the rate at which this engine reports a requirement as proven when the evidence does not support it, measured while executing this standard on this category. It is not the standard's error rate, and it is not a claim about klatchcoffee.com. All 5 of this page's proven rows were among the 160 read in that audit, and all 5 were adjudicated correct.
The bound is cluster-adjusted at ICC 0.2 because passing rows are not independent: rows from one store share that store's copy conventions. The four defect classes behind those 7 errors are named in full on the standard's own page.
The capture is committed to this project as fixtures/buyer-test/klatchcoffee.com.json.gz — the raw HTTP responses exactly as the store served them, so the sentences above can be checked against their source without fetching anything. The result is produced by the same engine that runs a merchant's own test, with the network swapped for that file.
Read the standard · The standard as JSON · How this is built and measured