Seeds from product context, once
Generation is idempotent. If a library exists it is returned rather than rewritten, so a stray click cannot throw away questions you have curated.
Monitoring
The questions to track, generated from what you sell
15
generated questions, the ceiling for one product
maxAutoPrompts in geo/prompts.go, chosen to match Basic's 15 checks a day
Picking prompts is where most AI-visibility tracking goes wrong. People track their brand name, watch it get mentioned, and conclude they are visible. Brand-name questions are the ones you already win. The questions that decide revenue are the ones where the buyer does not know you exist yet.
So the library is seeded from your product context: what you sell, to whom, and against which competitors. You can add and edit questions, and everything after that hangs off the list, since checks, corpus, leaderboard, and rank lookups all key on it.
Where it lives: Visibility in the dashboard. Regeneration is offered automatically after a repositioning.
What it does
Caps at fifteen for a reason
The cap is sized to the smallest plan's daily budget. A twelve-question library capped Basic at 360 checks a month against 450 sold, which is the sort of thing that quietly makes a plan worse than advertised.
Regenerates when you reposition
Change the description, keywords, or competitors and the library is flagged stale. The next baseline rewrites it before picking a question, once per repositioning rather than on every run afterwards.
How it works
- Manual questions sit alongside generated ones and are never overwritten by a regeneration.
- Rotation is by staleness: the question checked longest ago goes next, so a big library degrades into slower coverage rather than into ignoring half of itself.
- Each question can be deactivated without deleting its history, so its past citations stay in the corpus.
What it does not do
- Generated questions are a starting point. Nobody knows your buyers' phrasing better than you do, and the good libraries we see are half hand-written.
- More questions is not better. Fifteen questions on one engine and one daily budget means each question is checked about once a day.
- We do not track question volume. There is no reliable public source for how often a phrasing is typed into an assistant, and inventing one would be worse than admitting that.
Which plans have it
AI Visibility checks. Same library on every plan. The plan decides how many checks it can spend.
| Basic | Growth | Agency |
|---|---|---|
| 450/mo (15/day) | 1,200/mo (40/day) | 3,600/mo (120/day) |
Read the full plan comparison.
Live demo
See Prompt library on a real account, with no signup and nothing to configure.
Open the demoFrequently asked questions
Can I track competitor brand-name questions?
Yes, and it is one of the more useful things to add by hand. "Alternatives to <competitor>" tends to have the most citable corpus in a category.
What happens if I add more than fifteen?
The cap is on automatic generation. Manual questions are yours to add, but the daily check budget is what it is, so a longer library means each question is revisited less often.
How do I know a question is worth tracking?
If the answer to it would name a vendor, it is worth tracking. If the answer would be a definition, it is a blog topic, not a visibility check.
Related features
Monitoring
Every feature we publish AI visibility monitoring
Scheduled per-engine checks with a 0-100 score, tracked separately for being named and for being linked.
Citation corpusSource corpus
The accumulated set of pages the engines retrieved across every question and every run, deduplicated per URL and dated.
MonitoringThe mirror
The first-run screen: one buyer-intent question, the competitors the answer named, and whether you were in it.
Run it on your own product
Start with the free visibility check to see whether the engines name you today, then run the scan that shows which pages they used instead.