What this methodology covers
This page describes how Paz.ai measures AI shopping visibility for commerce teams. It covers the Shopping Visibility product and the implemented monitoring engines. Catalog optimization, distribution, and attribution are covered on the visibility platform page and the pricing page.
Engine scope
The implemented monitoring engines are Google AI Mode, ChatGPT, Perplexity, and Google AI Overviews.
| Engine | Role in Shopping Visibility |
|---|---|
| Google AI Mode | Monitored with per-engine appearance counts, found rate, position, and trends. |
| ChatGPT | Monitored with per-engine appearance counts, found rate, position, and trends. |
| Perplexity | Monitored with per-engine appearance counts, found rate, position, and trends. |
| Google AI Overviews | Captured and displayed with a tri-state outcome (present, not shown, failed). Diagnostic in Shopping Visibility and reported separately. |
Monitoring cadence
Monitoring runs on a scheduled cadence: weekly on Starter, daily on Growth and Enterprise.
- Starter: weekly monitoring for up to 500 products.
- Growth: daily monitoring for up to 5,000 products.
- Enterprise: daily monitoring for unlimited products.
Cadence reflects when Paz runs configured queries.
Query configuration and sampling
A merchant configures the shopper queries Paz monitors for their products and brand. Paz runs each configured query against each implemented engine and records what the engine surfaces. Queries are shopper-intent phrases a merchant wants to be visible for, such as a product category with a constraint.
Results are observations of what an engine surfaced at the time Paz ran the query, in the configured locale.
Definitions: what Paz records
| Term | Definition |
|---|---|
| Product card | A structured product result rendered by the engine, such as an image, price, merchant name, and link where the engine provides them. |
| Product mention | A natural-language reference to a merchant product in the response without a structured card. |
| Brand mention | A reference to the merchant brand in the response without a specific product. |
| Source citation | An outbound URL the engine cites as a source for the response. |
| Position | Where the merchant or its product appears in the response, recorded so changes can be tracked over time. |
| Found rate | The share of configured queries that surface the merchant as a product card, product mention, brand mention, or source citation. |
A brand mention without a URL is not a source citation. Paz records them separately so a merchant can distinguish being named from being cited.
How Paz reports per-engine visibility
For each configured query and each primary reporting engine (Google AI Mode, ChatGPT, and Perplexity), Paz records the count of each appearance type (product card, product mention, brand mention, source citation), the found rate (the share of the merchant's configured queries that surfaced the merchant), and the position (where the merchant appeared in the response, as observed). These are reported as observed values and as trends over time, not as grades.
The found-rate denominator is the set of configured queries the merchant set up for that engine, so found rate is reproducible from the query set and the recorded appearances. Appearance counts and positions come from the same recorded results. Trends compare those per-engine observations across completed monitoring runs; the interval follows the plan cadence and is not presented as a fixed calendar window. Google AI Overviews is captured with a tri-state outcome (present, not shown, failed) and reported separately.
Use the per-engine appearance counts, found rate, position, and trends described above to interpret and reproduce reported visibility.
How Paz treats Google AI Overviews
Google AI Overviews is captured and displayed with a tri-state outcome: present, not shown, or failed. It is reported separately from the three primary per-engine visibility reports.
Google AI Overviews does not trigger on every query. A non-trigger is recorded as an observation. The separate Brand Visibility GEO pipeline consumes the successful awareness results from all four engines.
How to interpret the results
- Treat each result as an observation of a configured query at the time and in the locale where Paz ran it.
- Monitoring runs on a scheduled cadence by plan (weekly or daily).
- Compare changes across completed runs using the same configured query set and engine.
- Use visibility changes as a signal for investigation rather than proof that a single optimization caused the change.
Update history
| Date | Change |
|---|---|
| 2026-08-15 | Published the methodology page with implemented engine scope, scheduled cadence, definitions, and Google AI Overviews diagnostic treatment aligned to the approved product brief dated 2026-08-09. |
| 2026-08-15 | Published how Paz reports visibility (found rate, position, appearance counts, and trends per engine) and stopped presenting the separate aggregate UI score as a reproducible, methodology-backed metric because approved public mechanics are not available. |
| 2026-08-15 | Refocused the public methodology on reproducible per-engine definitions and removed discussion of unpublished aggregate-score mechanics and internal product gaps. |
Related
- AI shopping visibility platform : what Paz measures and how to evaluate visibility software
- AEO and GEO optimization software for ecommerce : commerce-category fit for software selection
- Pricing : current plan details and cadence
- Editorial policy : primary-source, author and reviewer, and corrections standards