How-to

Read the Prompts overview

Filter the overview, read the headline, stat bar, and cards, and interpret visibility and share of voice.

The Overview tab of Prompts summarises every answer collected in a date range.

Set the filters

In the navigation rail, open Prompts → Overview.
Choose a date range. The default is the last month; you can also pick a custom range.
Narrow the set with Brand, Tags, and Models. Brand keeps Branded prompts (the prompt text names a brand) or Non-branded prompts. The Models dropdown lists AI assistants by name (ChatGPT, Gemini, Claude, Google AI Mode) and appears only when answers exist from more than one assistant.
Check the right end of the filter bar. It shows Data as of the last scan and when the next scan runs, or Awaiting first scan before the first run. Use it to tell an empty overview apart from one that has not been scanned yet.

All cards below follow these filters.

Read the headline

The top of the page shows AI visibility for the selected period: the share of answers that mention any of your own brands. A sentence underneath names your brand, its share of AI answers, the number of models, and your rank among the tracked brands.

AI Share of Voice — your brand’s slice of the total brand-mention pool, next to each competitor’s. Each answer counts at most once per brand.
Rankings — the leading brands. All rankings scrolls to the full table further down.
Open answers opens the Answers tab.

Read the stat bar

Total answers — how many answers were collected, with the prompt count underneath.
Prompts tracked — how many prompts the project monitors.
Models — how many distinct AI models produced those answers.
Avg sentiment — the average sentiment of those answers, from −1 to +1, with a label.

Read the cards

Visibility trend — one line per brand per day, showing that brand’s share of the mentions that day.
Top domains — the websites the models cite most often, including the pages Google cites in its AI Mode answers, with the number of answers referencing each one and its share of all answers in the range.
Rankings — each brand with its visibility percentage and trend badge, a Sentiment dot, and an average Position. Your own brands carry an Own badge, and each brand name opens that brand’s page. Here visibility is each brand’s share of all brand mentions, so the column sums to 100% for the period. The trend compares the range with the previous range of the same length. The table shows five brands per page.
AI model comparison — per prompt, which brands each AI model mentions, so you can see whether the models paint the same picture. View all opens the Prompts tab, narrowed to the selected tags.

Interpret the numbers

Read visibility and share of voice together. High visibility with a low share of voice means the models mention you, but mention competitors more often. A rising average position (a larger number) means the models name you later in their answers.

Empty and warning states

If your project has no prompts, a No prompts configured banner appears — no answers can be collected until prompts exist.
No mention data available yet under AI Share of Voice, or No brand data yet under Rankings, means no brand mentions were found in the filtered answers. Widen the date range or clear a filter.
Not enough data for trend means the range holds fewer than two scans.
If no prompts match the tag or Brand filter, AI model comparison shows No prompts match the selected filters. with a Clear filter link.