AgentReadyGo

How the AgentReadyGo score works

The score is deterministic: identical mission results give an identical score. The model decides what it observes, not what it is graded. This page documents the full calculation.

1. The journey stages

Each mission goes through a subset of stages. The agent declares the result of each one at the moment it clears it.

StageIdentifier
Site discoverydiscovery
Product searchsearch
Product understandingproduct_understanding
Comparisoncomparison
Variant selectionvariant_selection
Availability / stockavailability
Add to cartcart
Shippingshipping
Returnsreturns
Checkoutcheckout

Three verdicts are possible, converted into points: pass = 100, warn = 62, fail = 0. A stage outside the mission’s scope is not counted.

2. The dimensions

Stages feed eight dimensions, weighted by their real commercial impact.

DimensionStages aggregatedWeight
Discoverability
Capacité d'un agent à trouver le site, comprendre sa structure et localiser un produit précis.
discovery, search14 %
Product Understanding
Lisibilité machine de la fiche produit : caractéristiques, prix, cohérence avec les données structurées.
product_understanding14 %
Comparison
Possibilité de comparer plusieurs références sur des critères objectifs.
comparison8 %
Availability
Détermination fiable du stock et des variantes réellement achetables.
availability, variant_selection12 %
Cart
Ajout au panier sans ambiguïté et confirmation explicite du contenu.
cart14 %
Shipping
Disponibilité du coût et du délai de livraison avant le checkout.
shipping12 %
Returns
Accessibilité et clarté de la politique de retour.
returns8 %
Checkout
Capacité à atteindre le tunnel de commande et à en comprendre les étapes.
checkout18 %

3. Friction penalties

Each friction removes points from its dimension, capped at 45 points: beyond that, the stage score already reflects the failure.

26
Critical
15
High
7
Medium
3
Low
0
Info

4. The technical share

Machine-readability checks — robots.txt, sitemap, structured data, internal search — account for 30% of the Discoverability and Product Understanding dimensions, and nothing elsewhere. A technically flawless site on which agents fail gets a bad score, by design.

5. The overall score

A weighted average of the dimensions actually measured, with weights renormalized when a dimension was not tested. Two caps then apply:

6. The grades

85 – 100ExcellentAI agents generally complete the buying journey.
70 – 84SolidThe journey completes, with a few significant frictions.
50 – 69RiskySome missions fail or take abnormal effort.
0 – 49CriticalAgents hit major blockers.

7. What the score does not measure

It measures neither human conversion, nor visual design, nor raw technical performance. It measures one thing: whether an autonomous agent can carry a transaction through to the end on your public storefront.

How the score works · AgentReadyGo