The method, in full.

Frequency, not ranking.

The stable, meaningful quantity is not where a product appears in an answer but how often it is recommended for a specific buying need. List position is close to random across repeats; appearance frequency is stable. So the core metric is frequency by intent, and cross-engine agreement is reported as a separate number.

Three independent, web-grounded engines.

We measure across ChatGPT, Perplexity and Gemini in modes that browse the web and return citations. Parametric (no-web) answers are treated as internal exploration only — never as evidence for a badge.

• Neutral buying questions, many paraphrases, no brand names in the prompt.
• Observations are spaced over time, not taken in a single burst.

It beats chance, or it isn't a claim.

Each intent has its own null baseline — the frequency you'd expect by chance given how many brands plausibly populate that need. A product's observed frequency must clear that baseline, and we attach a conservative bootstrap confidence interval so the separation is statistical, not anecdotal.

Worked example (our own measurement, round 2026-10-04): for barefoot hiking the null sits at 27.6%; the record clears it at 95.3% across 3/3 engines — 143 of the 150 answers we recorded for that need. That record is the one served live at verify?claim=vivobarefoot|barefoot-hiking|US, so the figures on this page can be checked against it.

No echo chambers.

A signal that comes from one repeated citation is fragile. We measure the concentration of citing domains (an HHI over the cited sources); low diversity is flagged as a weakness and can disqualify a record. This stops a single affiliate page from manufacturing a recommendation. Known limit: Gemini currently returns citations as opaque redirect URLs, so its source-diversity score is not yet reliable — we treat Gemini's grounding as present but its domains as unresolved, and never rest a claim on Gemini alone.

Signal that drifts is revoked, not kept.

• Two clocks, not one: a record stays eligible while its evidence is within a 90-day window (C6). The badge on a store is current for 30 days from the measurement date. They are different clocks and we do not collapse them: the badge goes dated long before the record stops qualifying.
• Revalidation: rounds run monthly; stability over consecutive rounds is required.
• Revocation & expiry: if a product falls below its baseline or loses cross-engine consensus, the record is automatically and auditably revoked and the store badge stops showing. If evidence merely ages out of the badge’s 30-day window without a contradicting round, the badge shows its date — a dated fact — rather than a current claim, and stops showing only past the category horizon; it never displays a negative mark.

All must hold at once.

A (product × intent) pair is eligible only if every criterion below holds on fresh evidence. Thresholds are calibrated against observed data and updated as the program matures.

Where C5's 20 pp comes from, since it is the one threshold we set by measurement rather than by convention: two complete rounds one day apart already move by up to 12.7 pp with nothing having happened — that is sampling, not instability. A threshold below that would fire on noise. Over four weeks, real drift reaches 18 pp at the 90th percentile. So 20 pp sits above the noise and above the bulk of genuine drift, and it currently removes no record: the four Verified pairs move between 0.0 and 5.3 pp over a month. It is calibrated on one temporal interval, because that is how many exist; it will be re-examined once there are two.

You cannot pay to change any of these. Payment covers measurement, display and upkeep — never eligibility.

Reproducible from the record.

Every eligibility decision is reproducible from the per-query log: given a round id, an outside auditor can recompute C1–C7 and confirm the status. The method version travels with the badge.

The limits, stated.

Status: methodology v1.0 · grounded-only scope · Example figures are RecommendedByAI's own measured data for Vivobarefoot · barefoot hiking, round 2026-10-04.