How to get recommended by ChatGPT for "best X in [city]" questions

When a business owner asks ChatGPT “which accountant in Ghent is good for a small limited company?”, they do not get a list of ten links but a short answer with two or three names. Whoever is in that answer is on the shortlist. Whoever is not, does not exist for that buyer. For local service providers, getting recommended by ChatGPT comes down to one question: why does the model name your peer in the same city, and not you?

This article is about those local and practice-area recommendations: “best X in city Y”. For ChatGPT visibility in general, read our guide to ChatGPT SEO. If your competitor already gets named and you do not, start with your competitor gets mentioned by ChatGPT and you don’t. Here we focus on the local mechanism, on measuring per city and practice area, and on what to fix first.

Test it now: check with the free AI visibility checker whether you are already named today.

How does ChatGPT put together a local recommendation?

For a question that includes a place name or a clear local intent, ChatGPT usually searches the web live instead of answering from its training memory alone. According to OpenAI’s help page on searching with ChatGPT, ChatGPT rewrites your question into one or more targeted queries for external search partners, uses an approximate location based on your IP address for local results, and shows the sources the answer relies on.

That has two consequences for a firm or practice:

1. You must be findable in the search results ChatGPT requests. A firm that does not appear anywhere in the classic results for “accountant Ghent freelancers” rarely makes it into the selection the model chooses from.
2. You must be easy to summarise. The model picks sources that quickly make clear who you are, where you are and what you specialise in. Vague pages along the lines of “we help you with all your needs” give it no usable sentence.

The model weighs roughly the same kinds of signals as a local search engine. In its explanation of local ranking, Google describes three main factors: relevance, distance and prominence, and adds that more reviews and positive ratings can help your local ranking. You see the same logic in AI answers: does your offer match the question, are you nearby, and do other sources confirm that you are known and trustworthy?

Which sources decide whether you get named?

In the answers we analyse per city and practice area, the same five types of sources come back every time. How they fit together for local visibility in AI is also covered in local SEO for AI.

Two points deserve extra attention.

Specialisation per city. A firm with one general “Services” page almost always loses to a firm with a page “Bookkeeping for start-ups in Ghent” that explains concretely who it is for and how it works. The model looks for a sentence that answers the question. Give it that sentence.

Consistency. If your firm is in the register under an old name, in a directory with a previous address and on your site with a new phone number, the model doubts whether they are the same entity. Doubt means it would rather name a competitor it has no doubts about. How to straighten that out is explained in entity consistency. Optimising your Google Business Profile is usually the quickest win.

How do you measure your AI visibility per city and practice area?

You do not measure local ChatGPT visibility with one question, but with a fixed set of buyer questions per practice area and per city, asked several times. AI answers fluctuate: the same question can produce three different names today than yesterday. A single test says little.

This is how we approach it in our own analyses:

1. Write the buyer questions. Draft ten to twenty questions the way a real client asks them: “good dentist in Antwerp who treats anxious patients”, “employment lawyer in Leuven for employers”, “best accountant in Ghent for a sole trader”. Vary the wording, the city and the specialisation. How to find those questions is covered in prompt research for ChatGPT.
2. Repeat each question several times. In different sessions and on different days. Only then do you see a pattern instead of chance.
3. Record who gets named in each answer. You, your competitors, and which sources the model shows.
4. Calculate your share. In what share of the answers are you named? And for how many questions is a competitor named while you are not?
5. Look at the sources. The sources ChatGPT shows for a competitor usually point to exactly what you are missing.

The picture that emerges is often sobering. In many cities and practice areas we see the same two or three firms come back time after time, while firms that do invest online in a website or reviews are hardly named at all. The difference then rarely lies in the quality of the work, but in how easily the model can confirm their specialisation and location.

To go deeper, follow the steps of an AI visibility audit, or let the GEO checker test whether AI crawlers can read your site properly.

What do you fix first?

Start with what helps the model recognise you with certainty fastest, and only then with new content. This order works in practice:

1. Align your details. Name, address, phone and specialisations identical on your site, your Google Business Profile, your profession’s register and the main directories.
2. Get your business profile in order. The right primary category, your services, opening hours and photos. Ask satisfied clients for a review and reply to every review, including the critical ones.
3. One page per specialisation and region. Concrete, with the question as a subheading and a direct answer below it. No thin copies per town, but real content per client type.
4. Proof of expertise. A recognisable author or partner, qualifications and accreditations, publications or talks. The model prefers to name a firm with a face.
5. Mentions outside your site. Local press, trade journals, professional bodies, partner pages. A mention without a link counts too.

Only after that foundation does it pay to write more articles. A knowledge base without a clear entity behind it produces few recommendations.

What about professional rules for lawyers, dentists and accountants?

For regulated professions the question is not only whether you get named, but also how you communicate. Lawyers, dentists, notaries and accountants have their own rules on advertising and publicity. Superlatives such as “the best dentist in Antwerp”, comparisons with colleagues or promises about results are often not allowed or risky in these professions.

The good news: what AI models reward fits those rules well. Factual, informative content about your specialisation, your way of working and your accreditations is exactly what a model can summarise. You earn a recommendation with verifiable information, not with advertising language. We worked this out per profession:

• Lawyers: GEO for law firms, with the professional conduct constraints.
• Accountants and bookkeepers: SEO for accountants and GEO for accountants.
• Dentists: SEO services for dentists, with the rules for health-care advertising.

When should you have your local AI visibility measured?

You can run a first test yourself with a handful of questions. If you want a reliable picture per city and practice area, with repeated measurements, your share against the competitors named instead of you and a concrete action plan, that is work for a GEO agency. If you first want to understand why buyers already choose via ChatGPT, read your B2B buyer already has a shortlist and clients say they found you via ChatGPT.

Frequently asked questions

Does ChatGPT use my location for a local question?

Yes, usually an approximate one. According to OpenAI, ChatGPT can use an approximate location based on the IP address to show local results, and a more precise location if the user shares it. If the person names a city in the question, that city naturally carries the most weight.

Does a Google Business Profile help for ChatGPT too?

Indirectly, yes. A complete profile with the right category, correct details and recent reviews strengthens your local visibility in the search results AI assistants draw on, and it confirms your name, address and specialisation. It is rarely the only source, but it is one of the fastest to get in order.

How often should I measure my AI visibility?

Monthly with the same fixed set of questions is enough for most firms. What matters is that you ask the same questions every time, repeat them several times and keep the results, so you see a trend rather than a snapshot.

Can I pay to get recommended by ChatGPT?

You cannot buy an organic recommendation in an answer. What you can do is strengthen the sources the model relies on: your specialisation pages, your business profile, your listings in registers and directories, and your reviews. For advertising inside ChatGPT, read ChatGPT ads.

Want to know where your firm stands today in your city and practice area? Get in touch for an honest assessment.