← Back

How we score AI-readiness

Two complementary scores. Both are observable and reproducible — anyone can re-run them on their own store.

What we measure (23 checks)

Each check contributes points to the synthetic Agent-Readiness Score (0–100). Total possible: 32 raw points, normalized to 100.

Reachability & transport

REACHABLE

Site responds with HTTP 2xx

2 pt
HTTPS

TLS encryption active

1 pt
SECURITY_HEADERS

Security headers (CSP, X-Frame-Options, …)

1 pt
ROBOTS_AI

robots.txt has explicit AI agent directives

1 pt

Structured data presence

SCHEMA_ORG

Schema.org markup detected

2 pt
JSON_LD

Valid JSON-LD with @context and @type

2 pt

Product schema completeness

PRODUCT_NAME

Product.name field populated

1 pt
PRODUCT_IMAGE

Product.image field populated

1 pt
PRODUCT_DESCRIPTION

Product.description field populated

1 pt
PRODUCT_BRAND

Product.brand field populated

1 pt
PRODUCT_OFFERS

Product.offers object present

1 pt
PRODUCT_PRICE

offers.price (or priceSpecification.price) present

1 pt
PRODUCT_PRICE_CURRENCY

offers.priceCurrency present

1 pt
PRODUCT_AVAILABILITY

offers.availability present

1 pt
PRODUCT_AGGREGATE_RATING

AggregateRating attached to product

1 pt
PRODUCT_REVIEW

Review object(s) attached to product

1 pt

Product identifier

GTIN_DETECTED

GTIN/MPN identifiers (inline, microdata or feed)

2 pt

Machine-readable policies

POLICY_RETURNS

MerchantReturnPolicy attached or referenced

1 pt
POLICY_SHIPPING

OfferShippingDetails attached or referenced

1 pt

Proprietary MerchantStamp protocol (weight 0 per agent)

MERCHANTSTAMP_JSON

/.well-known/merchantstamp.json or agent.json present

3 pt
JSON_VALID

Manifest is valid JSON

1 pt
JSON_FIELDS

Required manifest fields present

2 pt
VERIFIABLE_CRED

W3C Verifiable Credential in manifest

3 pt

How per-agent visibility is computed

For each of the 5 AI shopping agents, we apply a weight in [0..1] to each check. Per-agent score = weighted average of passing checks ÷ sum of weights. Verdict: Readable (≥75%), Partial (≥40%), Invisible (<40%).

Proprietary MerchantStamp checks (manifest, Verifiable Credential) carry weight 0 in per-agent scoring — no public AI agent reads them today. They only contribute to the synthetic Agent-Readiness Score.

The 5 AI shopping agents we report on

Sources

Per-check weights are anchored to public documentation from each agent owner where available, and explicitly marked as heuristic where not.