1. Create a project
A project tracks one brand. Give it the brand's name, its website domains (so VisiMention can spot when an AI cites your own site), a category, the competitors you want to compare against, and a target market.
The target market sets the language and region your measurements run in, separate from the language you read the app in. Prompts and reports keep the market they were created under, even if you switch the project to a different market later.
2. Add prompts
Prompts are the questions your customers ask AI assistants, like "what's the best X for Y?". Each report asks these questions and scores how your brand comes up in the answers.
Write your own, or have AI generate a researched set from the project page for 3 credits. Either way, aim for questions a real buyer would ask, not questions that already name your brand.
3. Run a report
Choose which AI assistants to ask: any combination of Claude, GPT, Gemini, and Perplexity. You can also ask each prompt up to five times per provider. Repeat samples smooth out the natural randomness of AI answers.
Credits are weighted by provider for each prompt and sample, and you'll see the projected cost before you run. Progress updates live, and failed provider calls are never billed.
4. Read the results
Every answer gets scored on a few simple questions: did your brand get mentioned? Was it recommended, or even the top pick? Did the answer cite your site, or frame you negatively? And which competitors showed up? The report rolls all of that up into rates, competitor standings, prompt-level coverage, and the sources the answers cited.
Understanding your metrics explains what each rate means, why numbers move between runs, and when a change is worth acting on.
5. Work the opportunities
Open the Opportunities section on each report to see its ranked action list: questions where you're missing, sources that favor competitors, and answers that frame your brand negatively. Each list is based on that report's answers.
Want the short version? Ask for an AI summary of the whole list (1 credit).
6. Put it on a schedule
When your setup feels right, schedule daily or weekly runs from the project's reports page. Two email toggles sit next to the schedule: a digest to members whenever a run finishes, and change alerts for when a run's visibility shifts significantly. Alerts cover manual runs too.
Sometimes a scheduled run can't start, usually because the project has no prompts for its market or you're out of credits. When that happens, the reports page and a heads-up email tell you exactly what's blocking it.