How agent-ready are the leading e-commerce brands?

Where the leaders fall short.

Median score per area, across the brands where the area could be measured.

The most common gaps.

1. 1. Machine readable capability manifest 12 of 12 sites fail this check · Act There is no manifest telling an agent what your site is capable of.Fix: Publish /.well-known/mcp.json describing your available tools. It is a small static file and it is how an agent decides you are worth interacting with rather than scraping.How to fix it
2. 2. Products stated as machine readable offers 8 of 8 sites fail this check · Commerce Your products are pictures and prose to an agent. It has to guess the price by reading the page, and a guessed price is one it will not commit to.Fix: Emit Product JSON-LD on every product page with an offers block carrying price, priceCurrency, availability as a schema.org URL, and sku or gtin13. Missing here: a Product block, a price, a currency, stock availability, a SKU or GTIN.How to fix it
3. 3. Whole catalogue available in one machine readable place 8 of 8 sites fail this check · Commerce An agent has to discover your products one page at a time. Most give up long before they have seen your whole range.Fix: Publish a product feed an agent can fetch in one call, with id, title, price, currency, availability, image and link per item. Reference it from llms.txt and your commerce discovery document so it can be found without guessing.How to fix it
4. 4. Stock and variants exposed 8 of 8 sites fail this check · Commerce
5. 5. A customer can give their agent access 6 of 6 sites fail this check · Delegate
6. 6. WebMCP tools an agent can call 11 of 12 sites fail this check · Act
7. 7. Rules for agents are written down 11 of 12 sites fail this check · Delegate
8. 8. Agentic commerce endpoint (UCP or ACP) 7 of 8 sites fail this check · Commerce
9. 9. llms.txt briefing for AI 10 of 12 sites fail this check · Comprehend
10. 10. Machine readable business facts 9 of 12 sites fail this check · Comprehend

Every score, no names.

Each bar is one of the 22 brands we could scan, highest first. Brands are counted, not named. 3 more could not be scanned at all.

How we chose and measured.

Who: Ranks retailers by 2025 U.S. retail sales (in-store plus online); two entries without a single consumer online store were skipped, so source ranks run to 27. Source: National Retail Federation (NRF), compiled by Kantar, Top 100 Retailers 2026 List (2026-07-01). Sneeze It clients are left out.

When: each brand's main website was scanned once, October 25, 2026, by AgentReadyBot, which identifies itself on every request, obeys robots.txt and never tries to get past a bot wall. Public pages only. Sites change, so a brand's score today may differ. We rescan every month. The full method is on the methodology page.