Rubric / Actionability
Primary action reachable
journey.primary_probe
weight 2model-assisted
A read-only LLM-driven probe can identify the primary offering and either its price or its primary call-to-action.
Definition
Check ID
journey.primary_probe
Category
Actionability
Weight
2
Counts toward the score
Yes.
Evaluated by
A language model participates, with a pinned model, prompt and temperature.
Standard maturity
established
Canonical spec
None. This check has no published external specification — it is an AgentSpeed rule.
Introduced in
r2026.04.1
Retired in
Still active.
History
Every change to the instrument— including the versions that changed this check
Machine-readable
/rubric.json— this check, and every other, as data
How often this check is right
Declared gap. llm_assisted: the runner returns SKIP unless ANTHROPIC_API_KEY is set, so an offline fixture can only observe the disabled path. Calibrating it requires the recorded-provider harness in packages/ai, tracked separately from this corpus.
Corpus v1, measured under rubric r2026.11.0. Full method and every other check at /rubric/accuracy.
How to fix it
If agents cannot identify what you sell within 3 steps, your primary-offer page is under-structured. Add a visible headline, price (or "contact us"), and canonical CTA.
Does your site pass this check?
Free scan, 30 seconds, no signup — this check and the other 35, with the exact evidence for each verdict.
Scan my site →