A report has three kinds of settings: which AI platforms answer, the market the prompts are asked in, and the prompts themselves. This article covers each one. For the steps in order, see Creating a report.
Every plan can use all six. Each answer is stored with the pages it cites and the model that gave it.
AI platform | Made by |
|---|---|
ChatGPT | OpenAI |
Claude | Anthropic |
Gemini | |
Grok | xAI |
Perplexity | Perplexity |
AI Mode | Google, as Google AI Mode (AI Overviews) in Google Search |
A new report starts with ChatGPT, Claude and AI Mode. Pick at least one.
Tip: Google does not show an AI Mode answer for every search. When it shows none for a prompt, that answer says so.
1 credit asks one question on up to 3 AI platforms; 4 to 6 use 2. The form shows the cost per prompt for your selection before you run anything.
AI platforms selected | Credits per prompt |
|---|---|
1, 2 or 3 | 1 |
4, 5 or 6 | 2 |
So adding a second or third AI platform is free, and all six cost the same as four. See Understanding credits.
ChatGPT Search and Claude Search no longer run. Old reports keep their answers, and running one of them again uses ChatGPT and Claude instead.
The market decides which buyers you are measured against: AI names different brands in different countries, languages and cities.
Where your buyers are. The prompts are written and read for that country, and it sets the language until you pick one yourself.
The language your prompts are written in and the answers are read in. It starts as the main language of the country you picked; change it if your buyers use another one.
A city or area, for example "Miami, FL" or "London". Use it for a business that serves a place:
Clinics, restaurants, agents and local services
Regional companies
Anything people search for "near me"
Leave it empty for national search: online shops, software, and brands that sell everywhere.
Tip: To track several markets, create a Scheduled Report and add one location per market. Each run leaves one report per location, so you can compare them.
After the brand analysis, Rank Prompt suggests categories from your site, such as "CRM for small business" or "Email marketing tools". Select up to 5, or Add custom category.
Choose how many prompts to write per category (up to 20). The total shows next to it. A report holds up to 50 prompts.
Prompts | Credits on 1 to 3 AI platforms | Credits on 4 to 6 AI platforms | Good for |
|---|---|---|---|
5 to 10 | 5 to 10 | 10 to 20 | A quick check |
15 to 25 | 15 to 25 | 30 to 50 | A standard report |
30 to 50 | 30 to 50 | 60 to 100 | A full audit |
On the Write your own tab, type your prompts, each with a category. Type a new name in the category field to create one. Paste several prompts at once and they are split into separate prompts.
Good prompts read like something a buyer would type:
"What is the best CRM for a 10-person sales team?"
"What are the best alternatives to HubSpot?"
"HubSpot vs Salesforce for a small business"
"Which email marketing tool integrates with Shopify?"
On the Test visibility step you can edit or delete any prompt, add custom prompts and filter by category. Nothing is charged until you click Analyze visibility.
Running a report again after every prompt was analyzed replaces the results and charges the credits again.
To compare settings, run another report:
Duplicate report on Visibility > Reports copies a report's prompts into a new one. Change the location and each prompt is rewritten for the new place; change the language and you may want to translate them. Check the prompts before you create it
Create report starts from scratch on the same brand
Schedule on a report puts its prompts on a Scheduled Report
Each report is its own snapshot, so you can compare them side by side.
Email [email protected] and I'll help.
