Agentic Readiness Grader.
When ChatGPT Shopping or Google AI Mode tries to draft your product into a cart, six signals decide whether the transaction can even start. The grader checks all six — UCP profile, ACP discovery, native_commerce opt-in, feed health, Product JSON-LD, robots.txt — and returns a 0–100 composite with prioritized fixes.
Rate limit: 1 run per 30 seconds per IP. The grader reads only public endpoints.
The six checks, and what fixes each one
| Check | Why it gates agentic commerce | Fix guide |
|---|---|---|
/.well-known/ucp profile | Required for Google's Universal Commerce Protocol. Without it the store cannot participate in AI Mode checkout at all. | UCP guide |
/.well-known/acp.json discovery | Proposed discovery file for the OpenAI/Stripe Agentic Commerce Protocol. RFC-stage as of mid-2026 — flagged as informational, not a failure. | ACP guide |
native_commerce opt-in | Per-SKU UCP eligibility flag, usually shipped via a supplemental Merchant Center feed. No flag, no agent checkout for that SKU. | UCP guide |
| GMC feed health proxy | Disapproved or misclassified feed items are excluded from agent surfaces before any protocol logic runs. | Agentic commerce |
| Product JSON-LD completeness | Agents resolve price, availability, and identity from schema. Missing gtin or availability fields break cart drafting. | Schema for AI search |
| robots.txt AI-crawler admittance | 11 bots checked. A blocked crawler cannot read the PDP, which removes the SKU from research and checkout paths alike. | Crawl surface guide |
How to read the score
The composite weighs the six checks roughly evenly, with one asymmetry: the binary signals — robots.txt admittance and the /.well-known/ucp profile — count hard against the composite when failed, because they block downstream work no matter how clean the catalog is. Bands: 80–100 ready; 60–79 partial readiness, usually robots.txt drift or thin JSON-LD on top sellers; 40–59 work to do, treat the score as a planning input for next quarter; below 40 foundational gaps — read make my store agent-ready before re-running.
Why this matters now: agent-completed checkout shipped in stages through 2025–2026. ChatGPT Shopping and Perplexity Buy with Pro already draft carts; ACP and UCP pilots complete purchases agent-to-store. Stripe's ACP documentation describes the checkout flow the discovery file feeds. The protocols are young and the grader hedges accordingly — RFC-stage items are reported as informational. What is not speculative is the dependency chain: no crawler access means no research visibility, no schema means no cart drafting, no UCP profile means no AI Mode checkout. For the strategic picture, see the agentic commerce optimization guide.
Protocols change monthly. Your score should be re-checked weekly.
eCommerce Insights runs the agentic-readiness checks on a schedule, per SKU, and pairs them with citation tracking across six engines — so you see both whether agents can transact and whether engines recommend the product in the first place. See the agentic commerce solution.
Ask AI about the Agentic Readiness Grader
Have your favorite AI engine summarize this tool for your storefront.
Frequently asked questions
What does the Agentic Readiness Grader actually check?
native_commerce opt-in detection, the /.well-known/ucp profile, the proposed /.well-known/acp.json discovery file (flagged RFC-stage), Product JSON-LD completeness, and robots.txt admittance for 11 AI crawlers. Top three findings free; the rest unlock with an email.What is agentic commerce readiness and why does it matter in 2026?
Is this the same as the AEO Grader?
What does the 0–100 composite mean?
/.well-known/ucp — weigh heavily when failed because they block downstream work no matter how clean the rest of the store is.Do I need /.well-known/acp.json today?
Six checks. One score. Re-run weekly.
The grader turns "are we ready for agentic commerce?" into an answerable question.