A number from 0 to 100 that reflects how complete and unambiguous your product page data is for ChatGPT, Gemini and Copilot, including whether brand, identifiers, price, availability and variants are present, valid and consistent. It is calculated from the public pages Viplor reads during an audit, for your store and each product.
The Agents score checks 19 binary criteria marked Met, Not met or Not checked. Not checked criteria are not counted. Its category weights are C1 16, C2 34, C3 38, C4 4 and C5 8. The score is 100 times Met points divided by verified points, rounded half up. A proven Not met result for B1 or C4 caps the score at 49. A store that reads well for shoppers can still score low. D3 and D3b, and D5 and D5b, are separate steps. Many Shopify themes do not include shippingDetails, MerchantReturnPolicy or itemCondition in their product data by default.
B4 is worth 11 points and requires a valid GTIN with 8, 12, 13 or 14 digits and a valid check digit. An MPN or SKU does not count. Robots checks follow four cases: a named ViplorBot opt out means no score and an opt out message; a platform default rule, such as Shopify blocking /cart, is Not checked; a merchant added rule for all robots that closes a page useful for buying is Not met and the rule is stored; anti bot blocking makes C1 Not met and leaves the other points Not checked.
Scores map to three bands:
- Incomplete (0–49): Key product fields are missing from your pages' data.
- To complete (50–84): Some of the product data is in place; important gaps remain.
- Well filled (85–100): The product data on your pages is filled in for the checks that apply.
The band describes the data on your pages, not how any assistant will treat your store.
Some explanatory text in a report is written with AI and can contain mistakes, so review it before acting on it.