What local tracking does and does not measure

Local tracking answers one specific question: when an AI assistant is asked this prompt from this city, does it mention you? It is a precise tool, and precise tools have edges. Knowing where those edges are stops you from reading a city result as something it is not.

It measures a requested location, not a guaranteed one

When you enable local tracking for Chicago, every check is sent to Google AI Mode with Chicago as the search location, the same way a person in Chicago would be treated. The answer you get back is what that request returned. It is strong evidence of what a local customer sees, but it is not a promise that every fact in the answer is about Chicago, and it does not tell you what a specific person on a specific phone would see, because AI answers also vary with personalization and history. Treat repeated checks over weeks as the signal, not any single answer.

Today it runs on Google AI Mode

Local checks currently run on Google AI Mode, which is the model that can be targeted to a city. Your other tracked models keep answering from your brand's country in your standard tracking. When more models become available for local tracking, the prompt's Local tracking view will show you which location each model can support before you confirm anything. Until then, a local result is a Google AI Mode result and should be described that way in any report.

One city per prompt

A prompt can track one city at a time. If you need the same question measured in Chicago and Dallas, add the prompt twice with a small wording difference, or rotate cities over time and compare the windows. Changing the city starts a fresh history for the new city and keeps the old one intact, so switching never loses data, but it does not let you compare two cities side by side inside one prompt.

Local results stay out of your score

Your AI Visibility Score, the prompt table, the Overview charts and your competitor comparisons are all built from standard tracking only. Local answers are stored separately and never enter those numbers. That is deliberate: a brand that turns on ten local checks in a city where it is strong would otherwise inflate its headline score without anything changing in the rest of the market. If you want a local figure in a report, take it from the Local tracking view of the prompt.

Missing checks are not zeros

A local check can be pending, failed, or returned but not analysable. None of these count as "your brand was not mentioned". The Local performance panel counts brand appearances only across checks that completed and were analysed, and it says "No completed checks" rather than showing 0% when nothing has finished in the selected range. A low number of completed checks in a short window is a reason to widen the date range, not a verdict.

Capacity and cadence

Each brand can hold up to 10 prompts with local tracking, and each local check runs on the same schedule as your standard analysis. Local checks do not retry on their own: if a provider request fails, the failure is recorded and the next scheduled run tries again. Exports, Looker Studio, the REST API and the MCP connector currently expose standard tracking data, not local answers, so a local figure has to come from the dashboard.