To check what ChatGPT says about your practice, open a fresh session (logged out or a temporary chat), turn on web search, and ask like a patient: "best cosmetic dentist in [your city]." Note whether it names you, a competitor, or no one. Repeat over a few days, because AI answers shift. Prefer to skip the manual runs? Our free checker reads all three engines in about two minutes.
How do I check what ChatGPT says about my practice?
Open a clean ChatGPT session with web search turned on, then ask a patient-style question such as "who is the best cosmetic dentist in [your city]?" Read which practices it names, save the answer with the date, and run it a few more times. The goal is to see your practice the way a prospective patient sees it, not the way you already know it.
Follow these steps in order. Each one removes a way the test could quietly mislead you.
- Start a clean session. Log out, or open a temporary chat, so your history and saved details don't shape the answer. You want the response a stranger would get.
- Turn on web search. ChatGPT answers questions about local businesses by searching the live web, so make sure browsing or search is active for the query.
- Ask like a patient, not an owner. Use the phrases patients actually type, such as "best cosmetic dentist in [city]." Do not search your own practice name yet; that only tells you it exists, not whether you get recommended.
- Read who gets named. Note whether the answer lists your practice, competitors, directories like Yelp or Healthgrades, or says it can't recommend a specific dentist.
- Save it with the date. Screenshot the answer and write down the day. AI answers change, so a dated record is the only way to see whether you're gaining or losing ground.
- Repeat. Run each query three to five times across different days. One answer is only a snapshot, because AI results shift from run to run.
If you'd rather not do this by hand, our free AI visibility checker runs these queries across ChatGPT, Perplexity and Gemini for you and returns a single read in about two minutes.
Which queries should you test?
Test the phrases patients actually use, not your practice name. Patients describe a need ("Invisalign dentist near me"), a location, and sometimes a constraint like insurance or Saturday hours. Run one query per intent, swap in your city and neighborhood, and check whether a real result would send that patient to you.
These seven cover the intents that send most new patients to a dentist. Replace the bracket with your city, then run the neighborhood version too.
| Patient intent | Example query to test | A strong result looks like |
|---|---|---|
| Cosmetic / veneers | "best cosmetic dentist in [city]" | Your practice named in the shortlist |
| Invisalign / aligners | "Invisalign dentist near me in [city]" | You listed among the Invisalign providers |
| Implants | "dental implant specialist in [city]" | You named, with your specialty noted |
| Availability | "[city] dentist open Saturday" | You appear when hours match the request |
| New patient | "good family dentist in [city] accepting new patients" | You listed as open to new patients |
| Insurance | "dentist in [city] that takes [insurance]" | You named for the plans you accept |
| Brand check | "is [your practice] any good?" | An accurate summary of your reviews and services |
The brand check is the one query where using your name is the point. It shows you what an AI tells a patient who already heard of you, which is often the last step before they book.
Why one test isn't enough
One run is a snapshot, not the weather. AI answers are rebuilt each time and pull from a shifting set of sources, so the same question can name you today and skip you next week. According to a 2025 Profound analysis of about 80,000 prompts per engine, roughly 40–60% of the domains an AI cites for a given question are completely different one month later. Judge your visibility by how often you appear, not by a single result.
Here is how much the sources move in a single month, by engine. The takeaway is not the exact figure but the size of the swing: checking once and stopping is like reading one day's weather and calling it the climate.
| AI engine | Cited domains that change within a month |
|---|---|
| Google AI Overviews | ≈59% |
| ChatGPT | ≈54% |
| Perplexity | ≈41% |
Source: Profound domain-drift analysis, 2025 (≈80,000 prompts per engine, June–July). tryprofound.com
So run each query three to five times over a couple of weeks and track the pattern. This is exactly how we read our own city scans: not "did a practice appear once," but "how consistently does it appear." You can see the method behind that in how we measure AI visibility.
How to check Perplexity and Gemini too
ChatGPT is one of three engines patients use, and each finds businesses a different way, so check all three. ChatGPT reads Bing's web index, Perplexity reads the live web with visible citations, and Gemini leans on Google's index and Google Business Profile. Ask each the same patient-style question and note who it names.
The table shows where each engine looks and how selective it is. The recommendation rates come from a 2026 study of nearly 350,000 business locations, and the gap explains a common surprise: a practice can own the Google map pack and still be missing from ChatGPT.
| Engine | Where it finds local businesses | How often it recommends a given location |
|---|---|---|
| ChatGPT | Bing's web index (it searches Bing, scans the top 20–30 results, then applies its own logic; no direct Google access) | 1.2% |
| Perplexity | The live web, with visible citations and a preference for fresh pages | 7.4% |
| Gemini / Google AI | Google's index plus your Google Business Profile | 11% |
| Google local 3-pack (for comparison) | Google Maps and Business Profiles | 35.9% |
Sources: recommendation rates from SOCi's 2026 Local Visibility Index, ~350,000 locations across 2,751 brands (Search Engine Land); ChatGPT's reliance on Bing per Damian Rollison, Search Engine Land, 2025 (searchengineland.com).
Because each engine pulls from a different place, a weak result in one does not predict the others. That is the whole reason to check all three rather than assume ChatGPT speaks for every AI a patient might use.
What if your practice doesn't show up?
If ChatGPT names competitors or no one, the usual causes are simple: your site isn't in Bing's index, your business details don't match across platforms, or your reviews sit below the level AI engines favor (around 4.3★ for ChatGPT). Each of these is fixable, and none requires paying an engine for placement.
Start with indexing and consistency, then reviews. For the full sequence, read how to get your dental practice recommended by ChatGPT. And if being invisible feels like your problem alone, it isn't: across nearly 350,000 locations, ChatGPT recommended only 1.2% of them (SOCi, 2026), so most practices sit exactly where you do. That low bar is also what makes it reachable. For a local, dentist-specific breakdown, see our AI visibility report for Charlotte dentists.