Arenza is now part of the OpenAI Partner Network 🎉
← State of Agentic Commerce
Agentic Commerce Score · scanned 2026-07-23 · rubric v0.2

dossier.co

90/100
grade A
agent-buyable ✓
platform: shopify

Can an AI shopping agent buy from dossier.co?

As of 2026-07-23, yes: dossier.co meets the agent-buyable bar with an Agentic Commerce Score of 90/100 (grade A). The failing checks are: Product image alt text.

95
Discover — can agents fetch + read the store? (30%)
86
Evaluate — can agents parse + trust the products? (45%)
90
Transact — can an agent complete a purchase? (25%)

Discover — can agents fetch + read the store?

AI crawlers allowed (robots.txt)
No AI shopping crawler is root-blocked in robots.txt.
Homepage readable without JavaScript
Homepage serves ~1162 visible words of real HTML (no JS needed).
Sitemap discoverable
Sitemap found.
! llms.txt present
No /llms.txt (emerging convention — counted as a soft gap, not a blocker).

Evaluate — can agents parse + trust the products?

! Machine-readable product catalog
No open product feed — agents must crawl page-by-page; 3/3 sampled product pages carry complete Product JSON-LD.
Required fields (title/image/price/description)
No feed; from 3 sampled product page(s), Product JSON-LD carries 100% of the four required fields on average.
Product JSON-LD (Offer: price/currency/availability)
3/3 sampled product page(s) carry Product JSON-LD with a complete Offer (price + priceCurrency + availability); 3/3 carry any Product schema.
Brand + product identifier (sku/gtin/mpn)
3/3 sampled product page(s) expose both brand and an identifier (sku/gtin/mpn); brand alone on 3/3.
AggregateRating in Product JSON-LD
3/3 sampled product page(s) expose machine-readable review ratings.
Product image alt text
9% of content images on sampled product page(s) carry non-empty alt text.
Description depth (≥120 chars)
3/3 sampled product page(s) expose a quotable description (≥120 chars) in Product JSON-LD.

Transact — can an agent complete a purchase?

Agentic-checkout rail (platform prerequisite)
Platform: shopify. Shopify asset/runtime markers in homepage HTML.
Machine-readable price + availability
No feed; 3/3 sampled product page(s) expose price + availability via Offer schema.
! Per-variant stock readable
No feed: product-level availability is readable from Offer schema, but per-variant stock is not exposed.
Shipping + returns policies (with terms)
Shipping and returns policies fetched, with an explicit return window an agent can read.

Highest-impact fixes

  1. Write descriptive alt text on product images — it is the only thing a text-mode agent can read about your photography.
  2. Give agents a machine-readable catalog: keep an open product feed (on Shopify, /products.json) or at minimum ship complete Product JSON-LD on crawlable product pages.
  3. Expose stock per variant (size/colour), not just per product — an agent that cannot tell which variant is in stock will not complete the order.
  4. Add /llms.txt — a short markdown map of your key pages for AI systems (llmstxt.org).

Is this your store?

This is a point-in-time scan of public signals (2026-07-23) — if you have shipped fixes since, re-run it in ten seconds: npx agentic-commerce-score dossier.co.

ACS covers whether agents can buy from you. The other half is whether AI assistants recommend you over competitors — run Arenza's free Agentic Visibility Score or write to hello@arenza.ai.

Think a check is wrong? Every result carries the evidence it was based on, and the scanner is open source — so a disputed score is a reproducible question, not an opinion. Mail hello@arenza.ai and we will re-scan, correct the published page if we got it wrong, and note the correction. Fixed the gap instead? Tell us and we will re-scan and update this page.