Skip to main content
Prompt monitoring is the practice of running a fixed set of buyer questions against answer engines on a repeating schedule, so that changes in visibility can be attributed to changes on your site rather than to changes in the question. The prompt set is the instrument. If it changes, the measurement is not comparable.

​
What makes a good prompt set

Unbranded. “best project management tool for agencies” measures competitive visibility. “Ryze pricing” only confirms you rank for your own name. Branded prompts inflate the numbers and teach you nothing. Buying intent. Questions a prospect asks when close to a decision, not general curiosity. Phrased as people speak. Full questions, not keyword fragments. People type sentences into assistants. Deliberately varied in framing. The same underlying need worded three ways can return three different competitive fields. Large enough to survive noise. Answer engines are volatile. A handful of prompts produces noise; a substantial set produces a trend.

​
Prompt categories worth separating

Read these as separate populations, because they behave differently and mixing them produces a meaningless average. Problem-led prompts are the tractable ones. They have correct answers, and a clearly written documentation page can supply them. Recommendation prompts lean on what the model already believes about brands, which content work moves slowly if at all. Platform-worded prompts have a structural ceiling. When a question is phrased around a platform, that platform’s own domains take most of the citations. Track them, but do not expect documentation to win them — a marketplace or app-store listing is the lever there, not a docs page.

​
How prompts work in Ryze

On the Queries page, the Prompts tab holds your tracked prompt set — up to 50 prompts per workspace, grouped into topics.
  • Topics — each prompt belongs to a topic (for example “project management for agencies”). One topic is branded — “Your brand vs competitors” — and doubles as competitor discovery; the rest are category topics. The table shows each topic with its prompt count and visibility %, and expands to the prompts underneath with per-engine results, score, and last run.
  • Suggested prompts — Ryze seeds 25 prompts across 5 topics when AI visibility is set up, and Suggest adds more server-side without duplicating what’s there.
  • Add your own — the add dialog lets you pick an existing topic, type a new one, or leave it ungrouped.
  • Daily runs — prompts run once per day. Re-running the same day only asks prompts that are new or previously failed, so adding two prompts doesn’t re-run all fifty.
The GEO tab shows a Visibility by Assistant matrix: your brand and the top brands across the answer engines, each cell the share of that assistant’s answers naming the brand, with your own row highlighted. See AI visibility metrics.

​
Keeping the baseline stable

  • Do not edit prompts mid-measurement. Changing wording resets comparability. Start a new set instead and track it separately.
  • Add, don’t replace. New prompts start their own baseline from zero.
  • Record the engine and date with every run, since engine behaviour changes over time.