How we build prompt sets - the Golden Prompt Set methodology

Questions this guide answers

• How does SolCrys choose which prompts to track?
• What is the Golden Prompt Set?
• How does SolCrys decide which prompts to monitor for my brand?
• Where do SolCrys's prompt sets come from?

Direct answer

We build a Golden Prompt Set (GPS) for every customer category by grounding on four real-world data sources: intent volume across major search and marketplace surfaces, trending questions from leading public community platforms, AI query volume signals, and live follow-up questions from supported surfaces where reliable. Every prompt we hand you carries projected query volume so you can prioritize the questions your buyers actually run, not the ones marketers wish they ran.

We treat prompt selection as the single biggest determinant of AEO data quality. If we track the wrong prompts, every chart in your dashboard is wrong - so the rest of this page explains exactly how we choose, what we deliberately exclude, and how you can audit our selection.

Three failure modes we built the GPS to avoid

We've watched AEO prompt selection go wrong in three specific ways. The GPS exists to avoid all three.

The four grounding sources

Every GPS is built from four grounded data sources. A prompt only enters the GPS if it can be evidenced from at least one source - preferably more than one.

What a Golden Prompt Set looks like in practice

The GPS candidate library for a category is usually larger than the set a workspace actively tracks. The tracked benchmark should match the customer's plan and scope: current public brand plans track 10 prompts on Free, 20 on Starter, and 60 on Pro; Agency plans track 30 prompts per client organization; Enterprise scope is confirmed during evaluation. The mix below is a design target for a generic B2B SaaS category, not a survey result. Actual mix is tuned per industry and per customer.

The metadata we attach to every prompt

Examples above use well-known public products purely for illustration. They are not taken from any specific customer's prompt set - your prompts stay private to your workspace. For every prompt in your GPS we attach metadata so you can prioritize.

• Projected query volume - our estimate of monthly run frequency on AI engines.
• Buyer journey stage - awareness, consideration, decision, or risk validation.
• Engine relevance - which AI engines this prompt is most likely to appear on, based on engine-specific patterns we've observed.
• Source provenance - which of the four grounding sources brought this prompt into your set, so you can audit our selection.

How your own prompts blend in

We treat the GPS as the foundation, not the whole thing. You know your buyers in ways we don't, so every workspace - including the Free AI Visibility Audit - lets you supply your own prompts as an alternative to, or alongside, the GPS. We default to running the GPS directly because it produces a more intent-aligned baseline than prompts drafted from scratch: every GPS prompt is grounded in our four-source evidence model, so customers who don't have time to author prompts still get a rigorous starting set. In ongoing workspaces, you can replace any GPS prompt with your own at any time, and our in-app suggestion panel recommends additions based on gaps in your current set, trending category discussion, and engine follow-ups we found in your own tracked responses.

The prompt sanity-check workflow is [coming soon]. Today, we treat off-topic prompts, brand-flattering prompts without comparative context, and duplicate prompts as review criteria during setup and customer review. When this ships in-product, flags will be guidance rather than gating.

How we keep the GPS stable

The GPS is designed to be a stable measurement benchmark, not a real-time prompt rewrite engine. Prompt changes are handled as review items with the customer during onboarding, regular measurement reviews, customer-requested replacements, or clear category changes such as a new entrant, pricing shift, or major news event.

What we are explicit about not promising

We've written this section because we'd rather you know the limits up front than discover them in your second quarter with us.

• We don't promise the GPS guarantees revenue lift. A perfect prompt set doesn't fix weak content or thin brand presence; it just measures the right things.
• We don't claim to replace human judgment. The slot we reserve for your own prompts exists because you know your buyers in ways we don't.
• We don't generate prompts from a single LLM. We refuse to ask one model to 'write 100 questions a buyer might ask' and call it research. Every prompt in your GPS has external evidence we can show you.
• We don't automatically change tracked prompts without approval. Prompt revisions are handled as review items with your team; newly added prompts start their own measurement history.

Why we publish this methodology

Most platforms in our category keep prompt-selection methodology opaque. We publish ours because trust is our product - if you don't trust how we chose your prompts, every chart we show you is meaningless. We want this methodology to be falsifiable: open any prompt in your GPS and we'll show you which of the four sources surfaced it. We want you to evaluate us before you sign, not after.

FAQ

Related guides