“How many prompts should I track for AI search?”
The honest answer depends on your footprint, initiatives, products, and competitive set. A practical rule of thumb helps when standing up an AEO/GEO program.
Try this heuristic: X [# of topic clusters] x Y [12–15 questions per cluster] = Z [# of AI search prompts to track].
This heuristic produces a representative sample you can use to measure AI search performance over time. Below is how to apply it—and how to make each prompt work harder.
Keywords from Google Search Console and Google Ads are a natural starting point. Just remember they’re not 1:1 with prompts:
Take “project management software.” In AI search, that can reasonably expand to:
AI platforms—ChatGPT, Gemini, and Perplexity—decompose a single prompt into sub-queries, retrieve sources across the web, synthesize results, and return one answer. You do not need to track every possible variation; a representative sample across business-relevant topics is sufficient.
As Scrunch data scientist Michael Iannelli put it in his post on measuring prompt performance: “Just like meteorologists don’t need to measure the temperature of every square foot of a city to report the weather, marketers don’t need to track each and every prompt to measure brand perception and competitor movement.”
Here’s a simple workflow.
Start with SEO keywords, paid search keywords, and the major product and content areas of your website. For tips on sourcing, see the monitoring section of our AI search guide under source prompts.
Group related items by common themes—use cases, competitors and alternatives, integrations, industries. Each group becomes a topic cluster (and later, a prompt cluster).
A competitor cluster, for example, might include:
Most clusters will map to 5–15 keywords. If you exceed that, split into multiple clusters.
Aim for 12–15 questions per cluster, covering the full buyer journey: awareness, advice, evaluation, and comparison. Include both branded and non-branded variants to capture users who do not yet know your brand by name.
Inform your prompts with real signals: SEO questions, PPC queries, and the questions your sales, success, and support teams field regularly.
Multiply topic clusters by questions per cluster. That output is your initial scope—then adjust up or down by cluster relevance.
As a rough guide:
| Company stage | Topic clusters | Questions per cluster | Total prompts |
|---|---|---|---|
| Startup / SMB | 3–100 | 12–15 | ~36–1,500 |
| Growth / Mid-market | 33–400 | 12–15 | ~396–6,000 |
| Enterprise | 133–4,000+ | 12–15 | ~1,596–60,000+ |
The more prompts you track, the more organization matters. Scrunch provides three layers of structure:
Not using Scrunch? A simple spreadsheet based on our prompt tracking framework works, too.
Phrase prompts for clarity and intent:
Think “What are the best online banks for small businesses?” not “online banking benefits.”
Data quality drives insight quality:
Track both—but prioritize non‑branded prompts to see where AI ranks and recommends you when users don’t ask for you by name.
Reality‑check your prompt set against what customers actually ask. Scrunch’s Trends feature helps you spot rising topics, new categories and competitors, and seasonal shifts so what you monitor matches what the market cares about.
Use Scrunch AI Referrals and Agent Traffic to connect visibility to outcomes: - AI Referrals shows human visits to your site from AI platforms - Agent Traffic shows which URLs AI crawlers hit most frequently
Compare your most visited or crawled URLs with your prompt list to find gaps and decide which AI platforms to prioritize.
Customer behavior changes, and your prompts should reflect that:
Traditional keyword tools estimate search volume for short phrases on web search engines. AI search works differently. Scrunch measures visibility and engagement signals across AI models using four core metrics:
| Metric | What it measures |
|---|---|
| Mentions | Whether your brand appears in AI answers for a given prompt |
| Citations | Whether the AI links to or references your content |
| AI Referrals | Human visits to your site originating from AI platforms |
| AI Agent Traffic | Crawler activity from AI agents actively retrieving your content |
These four metrics show where and how often AI systems surface your brand, which sources they cite, and whether those answers drive site visits—replacing the keyword-volume proxy used in traditional SEO.
Scrunch brings together monitoring, insights, and activation so you can improve how AI models see—and cite—your brand.
Yes. If you’re comfortable with keyword research, mapping to topics, and funnel‑stage content, you’ll feel at home. The keywords‑to‑prompts workflow uses familiar building blocks, and the platform layers on: - Cross‑model monitoring so you can compare performance by AI platform - Intuitive grouping and filters (topic, stage, persona, branded vs non‑branded) - Clear visibility metrics (mentions, citations) tied to outcomes (AI referrals, agent traffic)
The formula is simple; the practice is iterative. Start with a representative sample and refine as you learn. Teams that begin measuring now—while prompt tracking is still an early-mover advantage—build a clearer, more defensible picture of how AI surfaces their brand, with precision improving each cycle.
Build your prompt tracking strategy with help from Scrunch. Try Scrunch free for 7 days or schedule a demo to see it in action.