Skip to main content

Scoring Model

How Colter scores agent readiness across 5 dimensions. Weights, signals, score ranges, and how to improve.

TL;DR: Colter scores stores from 0 to 100 across transaction, discovery, ecosystem, content quality, and security. The fastest way to improve the score is usually UCP, ACP, JSON-LD, llms.txt, and security headers.

Formula

composite = round(
  transaction * 0.30 +
  discovery * 0.25 +
  ecosystem * 0.20 +
  content_quality * 0.15 +
  security * 0.10
)

Dimensions

DimensionWeightHigh-value signals
Transaction30%UCP, ACP, checkout capabilities, fast protocol endpoints, compatible PSP
Discovery25%JSON-LD, sitemap, llms.txt, ai-plugin.json, robots posture, Open Graph
Ecosystem20%Google coverage, OpenAI coverage, MCP, WebMCP
Content Quality15%Complete product schema, price, availability, images, SSR
Security10%HTTPS, HSTS, CSP, XFO, X-Content-Type-Options, rate limiting

Score Bands

ScoreMeaning
75-100Strong readiness
60-74Basic readiness
40-59Needs work
0-39Not ready

Agentic Commerce Level

Colter also emits an agentic_level and label:

LevelLabelMeaning
1Web FormsBasic site presence
2Descriptive SearchAgents can find and read the catalog
3PersistenceStronger agent identity and handoff support
4DelegationAgents can browse, cart, and checkout
4.9 maxProgress toward Level 5Level 5 behavior is not directly measurable today

Highest-Impact Fixes

FixTypical effect
Add UCPBig transaction and ecosystem lift
Add ACPBig transaction and ecosystem lift
Add complete Product JSON-LDDiscovery and content quality lift
Add llms.txtDiscovery and ecosystem lift
Add security headersSecurity lift

How To Use This Page

  • Use Check to see current scores.
  • Use Fix to get ranked improvements.
  • Use Verify when you need conformance evidence.

Next Steps