---
title: "Build AI tracking prompts from sampled query fan-outs"
description: "Build your AI visibility prompts from real fan-out data instead of guessing."
url: https://aeo.so/tactics/build-ai-tracking-prompts-from-sampled-query-fan-outs
author: "Paul Andre de Vera"
updated: 2026-11-15
---

# Build AI tracking prompts from sampled query fan-outs

Build your AI visibility prompts from real fan-out data instead of guessing. Run a seed question about 20 times, collect the sub-queries the AI searches for, cluster them, and turn the most frequent clusters into tracking prompts. Test each model separately, as Gemini, ChatGPT and Claude search and cite differently.

- Area: [Experiments & Case Studies](https://aeo.so/categories/experiments)
- Credited to: [Bernard Huang](https://aeo.so/experts/bernard-huang)
- Part of: [the aeo.so answer engine optimization checklist](https://aeo.so/categories)

The worked example, why this helps with AI search, and the original source are free for members: https://aeo.so/sign-in


Read the guide:

- [What is generative engine optimization (GEO)?](https://aeo.so/guides/generative-engine-optimization)
- [Is SEO dead?](https://aeo.so/guides/is-seo-dead)
- [What is query fan-out?](https://aeo.so/guides/query-fan-out)

## More in Experiments & Case Studies

- [Measure AI search with input, channel and performance metrics](https://aeo.so/tactics/measure-ai-search-with-input-channel-and-performance-metrics)
- [Check AI visibility tools against customer surveys](https://aeo.so/tactics/check-ai-visibility-tools-against-customer-surveys)
- [Use Microsoft Clarity to see what AI-referred visitors do](https://aeo.so/tactics/use-microsoft-clarity-to-see-what-ai-referred-visitors-do)
- [Check LLM-based content scoring against real readers](https://aeo.so/tactics/check-llm-based-content-scoring-against-real-readers)
- [Create content specifically for AI training data](https://aeo.so/tactics/create-content-specifically-for-ai-training-data)
