Agent readiness is not a vibe

A store does not feel agent-ready. It scores agent-ready.

Every scorecard we publish is a score out of 100, a letter grade, and a list of checks: what passed, what failed, and why. Each check is a task a machine customer must be able to complete, from reading a price to finishing a checkout.

Two rules keep the scores honest. First, every check is reproducible: another run, same store, same conditions, same result within tolerance. Second, every failure ships with evidence: the trace, the step, and the state the agent could not get past.

If a store fixes a failure, we rerun and the score changes. If a rerun disagrees, we investigate before we publish.

Sample scores on this site are labeled as sample until the first full run of the 500-store panel completes.