The questions we actually test
Every audit runs a set of guest-style prompts against ChatGPT, Gemini, Perplexity and Claude. These are the prompt families we draw from. Placeholders in braces are replaced with your business name and location.
Hotels & country houses
Stay-intent prompts covering location, occasion, budget and amenity.
- ›Best boutique hotels near {location}
- ›Where should I stay in {location} for a romantic weekend?
- ›Family-friendly hotels in {location} with a pool
- ›Country house hotels near {location} with a good restaurant
- ›Dog-friendly hotels in {location}
- ›Quiet hotels near {location} for a work trip
- ›Is {business} a good place to stay?
- ›Hotels near {landmark} with parking
Restaurants & bars
Dining-intent prompts covering occasion, cuisine, dietary need and timing.
- ›Best restaurants in {location}
- ›Where to eat in {location} for a special occasion
- ›Good Sunday lunch near {location}
- ›Restaurants in {location} with vegan options
- ›Late-night food in {location}
- ›Is {business} worth booking?
- ›Best tasting menu near {location}
- ›Restaurants near {location} that take large groups
Spas & wellness
Treatment and retreat prompts covering purpose, duration and price bracket.
- ›Best spa days near {location}
- ›Spa hotels in {location} with thermal facilities
- ›Where to go for a couples spa day near {location}
- ›Affordable spa breaks in {location}
- ›Is {business} good for a spa day?
- ›Wellness retreats near {location}
Golf
Course-selection prompts covering standard, access and stay-and-play.
- ›Best golf courses near {location}
- ›Golf breaks in {location} with accommodation
- ›Championship courses near {location} open to visitors
- ›Is {business} worth playing?
- ›Golf clubs near {location} with societies welcome
How prompt sets are built
Prompts are written in the language guests use when choosing where to stay, eat, book a treatment or play — not keyword lists. Each audit uses a mix of category prompts (where you compete against others) and named prompts (what an assistant says when someone asks about you directly).
Answers vary between runs, so a single result is never treated as proof. We record whether you appear, where you rank, how you are described and which sources the answer leans on, then track movement across repeat runs.
Pro accounts can add their own prompts and track mention rate, rank and share of voice per prompt over time.