Agent readiness checker
Paste a product URL and see what an AI shopping agent actually sees. The page is fetched once with no JavaScript executed — the same view a crawler gets — and scored on the signals an agent needs to read, price and trust your product.
Fetches the page once, without executing JavaScript — the same view a crawler gets. Nothing is stored.
Why this measures the right thing
Adobe measured retail product pages scoring 66% on machine readability in Q1 2026 — the lowest of any major page type — while AI-sourced traffic to those same sites grew 393% year over year. The demand arrived faster than the ability to serve it.
Almost all of that gap comes from one thing: pages built for eyes. Price and stock that only exist after client-side rendering are invisible to a client that does not render. Everything this tool checks is visible in the raw HTML or it does not count, because that is the standard an agent actually applies.
What a good score does and does not tell you
A high score means an agent can read your product and trust the values it finds. It does not mean assistants will surface you, and any tool implying otherwise is overselling. Brand-owned sites account for roughly 5–10% of the sources AI search draws on; affiliate content, publishers and user-generated content exceed 65% in key categories.
So treat this as the prerequisite rather than the strategy. Getting it right means the mentions you earn elsewhere lead somewhere an agent can verify — and getting it wrong wastes every one of them. The four signals that decide recommendations covers the rest.
Frequently asked questions
- What does this tool actually check?
- It fetches your page once without executing JavaScript and inspects the raw HTML for schema.org Product markup, an Offer price and currency, stock availability, a stable identifier such as GTIN, MPN or SKU, whether readable text exists before any script runs, robots directives, a canonical URL and a meta description.
- Why does it not run JavaScript?
- Because that is the point. A page whose price only appears after client-side rendering is a page an agent cannot read, and a checker that runs a headless browser first would report that page as fine. Measuring the raw HTML is what makes the result meaningful.
- Is my URL stored?
- No. The page is fetched once, analysed in memory and the result returned to your browser. Nothing about the check is written to a database or a log we retain.
- What is a good score?
- Above 80 means an agent can read your product with confidence. Between 55 and 80 usually means the markup exists but is missing availability or an identifier. Below 55 generally means either no structured data at all or a page that renders client-side — the latter being the more expensive to fix.
- Does a perfect score mean AI assistants will recommend my products?
- No, and it would be dishonest to imply otherwise. This measures whether an agent can read and trust your page once it reaches it. Whether you get surfaced at all depends heavily on third-party signals — reviews, publisher coverage, community discussion — which brand-owned sites do not control.