Prompts
The questions your customers ask AI — tracked per engine, on a cadence.
Prompts are the unit of GEO tracking: the questions your customers ask AI answer engines, each run against a chosen set of engines on a schedule. Every metric on the AI Visibility pages derives from prompt runs.
Anatomy of a prompt
| Field | Meaning |
|---|---|
| text | The question, 3–300 characters. Write it the way a customer would actually ask. |
| category | Free-form grouping (e.g. comparison, pricing, how-to). |
| engines | Which engines run it (default: ChatGPT, Claude, Gemini, Perplexity). |
| cadence | daily or weekly. |
| active | Off pauses it without losing history. |
Writing good prompts
- Ask like a customer, not a marketer. "best managed postgres for startups" beats "why is Acme great".
- Include comparison terms. "acmecloud vs hetzner" is where purchase decisions happen.
- Cover the buying journey: awareness ("what is X"), comparison ("X vs Y"), selection ("is X good for Z").
- Don't stuff your brand into every prompt. Unprompted mentions (the engine brings you up on a generic question) are the strongest signal you can get.
Running prompts
- Run all executes every active prompt against its engines.
- Single-prompt Run is available per prompt.
- Every
prompt × engineexecution costs 1 credit, billed per call: a same-day re-run replaces the earlier result snapshot (history is not stacked) but charges its credit again — only genuinely failed runs are refunded. - Quota: daily GEO runs per organization follow the plan (Free 10 → Agency
10,000) plus any platform bonus; the daily job (default 07:00 UTC, see
WORKER_*_CRON) skips prompts already run today and skips projects paused by billing.
What a run records
Each run stores the engine's full answer, the brands it mentions, the domains
it cites, and its data_source label (live vs sampled — see
Data sources). Mention detection matches
your project's brand names and aliases against the answer text, which is why
aliases matter (see Competitors).
Managing the set
Prompts are per project. A healthy set is 10–30 prompts across categories, reviewed monthly: retire questions nobody asks, add newly popular phrasings, and keep cadence weekly for stable terms and daily for volatile ones (pricing, comparisons, new entrants).