Build a prompt set
Your prompt library is the pool of customer questions you may want to track. Free runs the first 30 selected prompts once on ChatGPT. Plus tracks up to 80 editable prompts weekly on ChatGPT and Google AI Overviews. Pro tracks up to 200 editable prompts weekly across ChatGPT, Gemini, Perplexity, Google AI Mode, and Google AI Overviews.
Library and prompt set are different
The library can hold candidates for different regions and campaigns while the prompt set is the versioned selection that actually runs. Free runs 30 once; Plus selects up to 80 weekly; Pro selects up to 200 weekly. The Free library stays open after the first run, but its runnable set does not change.
How monthly versions work
Plus and Pro keep the current selection stable for a month so every result uses the same measurement population. Free keeps its initial set as a fixed snapshot.
Build the library
Add, import, and organize as many useful candidate prompts as your project needs. Adding a prompt to the library does not change the set that is already running.
Prepare next month's set
Select up to your plan limit, 80 prompts on Plus or 200 on Pro. You can revise that selection until the lock date shown in the product. Changes saved for the next set prepare future tracking; they never rewrite the current locked version.
Let the version lock
At the start of the next month, the prepared version becomes the current set. If you take no action, AppearIn AI carries forward the prompts in the existing selection using their latest library wording. Removed prompts and prompts tied to inactive products stay out.
Keep the weekly cadence
On Plus and Pro, the current version runs weekly throughout the month. Only one prompt set runs at a time for a project, and every run retains its version attribution.
What changes when a new version starts
Set-scoped metrics begin a new baseline. Use the Period control on Overview, Visibility, Mentions, Citations, and prompt-derived Actions to revisit an earlier version. Visibility can calculate direct month-to-month deltas when both versions use the exact same prompts and run settings.Think in customer intents, not features
A prompt is a question a real person might type into an assistant. The most useful sets cover the different reasons someone would ask about your category. Three intents matter most:
| Intent | What the customer wants | Example prompt |
|---|---|---|
| Informational | To understand the category or solve a problem | "how do startups keep track of projects?" |
| Commercial | To compare options before buying | "best project management tools for startups" |
| Navigational | To learn about a specific brand | "is Acme good for small teams?" |
Commercial prompts are where most visibility battles are won or lost, since that's where the AI engine recommends specific tools. But a set built only of "best X" questions misses the informational searches that introduce your brand earlier in the journey. Spread your prompts across the intents your buyers actually move through.
Write five to ten real questions
List how customers actually ask
Write each prompt the way a buyer would phrase it to an assistant, not the way you describe yourself. "Best project management tools for startups" is a real question. "Acme is the leading AI-powered workspace" is your tagline, and an AI engine will never be asked it.
Cover the intents that matter
Make sure your set includes at least one informational prompt, a few commercial ones, and a navigational one. Five to ten total is enough to start. Grow the library as you find gaps, then include the strongest candidates in a future monthly version.
Accept AppearIn AI's suggestions
AppearIn AI suggests prompts from your brand profile, category, features, and buyer context. Accept the ones that sound like questions your customers ask, edit the ones that are close, and skip the rest. During setup, your selections form the first set. On Plus and Pro, later suggestions join the library for a future version.
Group by intent or segment
Group prompts so you can read results by slice, for example commercial prompts separately from informational, or "startup" prompts separately from "enterprise". Grouping makes it obvious where you're strong and where a competitor owns the answer.
Run and schedule
Use the onboarding seed run for your first snapshot. Plus and Pro then refresh the same locked version weekly. Because the data is probabilistic, read the trend across several scheduled runs instead of treating one answer as a durable result.
Worked example
Suppose Acme makes project management software for startups. A solid starting set of seven prompts might be:
- "how do small startups keep projects organized?" (informational)
- "best project management tools for startups" (commercial)
- "affordable project management software for a small team" (commercial)
- "Beta vs Acme for a 10-person startup" (commercial)
- "project management tools with a free plan" (commercial)
- "is Acme good for early-stage teams?" (navigational)
- "what should I look for in a startup PM tool?" (informational)
Run this on Pro and you might find Acme is mentioned in the "best project management tools for startups" answer on ChatGPT, Perplexity, Google AI Mode, and Google AI Overviews, but Beta takes the top slot on Gemini. That difference is exactly what the set is for: it tells you which AI engine, and which intent, to work on.
What good looks like
A healthy prompt set has:
- Five to ten prompts, each phrased as a question a customer would actually ask.
- A mix of informational, commercial, and navigational intents.
- No near-duplicates, each prompt covers distinct ground.
- Grouping by intent or segment, so results are readable at a glance.
- No more than the plan limit selected, even when the library is much larger.
- Weekly runs on Plus or Pro, turning single answers into a trend.
Common mistakes
Describing yourself instead of asking like a customer. An AI engine is asked questions, not pitched taglines. "Best X for Y" beats "Acme is the leading" every time.
Too few prompts. One or two questions give you a sliver of coverage. If you don't ask the question, you can't see whether you appear in its answer.
Near-duplicates. "best PM tools for startups" and "top project management tools for startups" measure almost the same thing. Spend that slot on a different intent or segment instead.
Expecting a library edit to change this week's run. On Plus and Pro, the current version is locked for the month. Prepare the next version and check its lock date to know when the change will take effect. Free does not allow post-setup edits.