A San Francisco AI citation audit needs a precise service area because “San Francisco,” “Bay Area,” a neighborhood, and a nearby city are different location signals. The report runs the buyer-intent prompt set for the exact market, samples each API several times, and reports which businesses and sources appear for that defined place.
Local practices often describe themselves with several overlapping geographies. A firm may serve San Francisco from Oakland, a dentist may draw patients from one neighborhood, and an HVAC company may use a broad service area without a San Francisco address. Combining those cases in one prompt set makes the mention rate hard to interpret.
What the record changes
The audit therefore records the place phrase in every prompt and groups results by city, neighborhood, or regional variant. The entity pass checks whether the practice's site and listings describe the same service area without creating false locations. A nearby competitor may appear legitimately for a regional prompt, and the report states that fact without treating it as an error.
- The free check uses one service and one city so the first answer has a defined denominator and can be reproduced in a paid prompt set.
- A full report preserves verbatim dated API answers and computes mention and citation rates for the exact location wording used.
- San Francisco professional practices remain responsible for state and local advertising rules, and the audit provides no compliance opinion.
How to use this answer
An AI citation check defines buyer-intent prompts for one service and place, runs each prompt several times through the platforms' APIs, and records every named practice and cited source. The report uses mention and citation rates over a stated run count because a single answer can change on the next run. Entity checks then compare the practice's name, address, phone, service, and location pages across the sources that appeared.
- Choose the service, city, and buyer question before naming the practice you want to measure.
- Run each prompt several times on each API, save the verbatim dated answers, and calculate rates from the full run set.
- Inspect the cited directories, articles, and local pages for entity consistency, then prioritize fixes on surfaces the practice controls.
Where the service stops
Reality Contact, LLC runs prompts through platform APIs and reports dated sampled answers. API output is a proxy for consumer-app output and can differ from it. We report who appears and which sources the answer cites. We do not get a practice named, cited, ranked, or recommended, and we do not rate competitors. This is not legal advice or financial advice, and it is not advertising-compliance advice.
Sources: OpenAI web-search documentation; Perplexity Sonar documentation; Google Gemini grounding with Search.