GitHub Repository

Open-source AI visibility audit for ecommerce - see if ChatGPT, Gemini & Google AI recommend your store or your competitor's. Self-hosted, printable PDF report.

5 starsPython

Open-source tool for reverse engineering ChatGPT queries about brands

Name: Open-source tool for reverse engineering ChatGPT queries about brands
Availability: InStock
Author: biduskamil

by biduskamil·Jun 23, 2026·1 point·1 comment

Visit Project View on HN

AI Analysis

●MidNiche Gem

WildChat dataset matching for AI brand visibility, but e-commerce focus limits appeal.

Strengths

•WildChat dataset (~1M conversations) provides real query data instead of guesses.
•Self-hosted with Docker and sample dataset means instant evaluation without API costs.

Weaknesses

•Narrow e-commerce focus limits broader applicability beyond online stores.
•Depends on WildChat dataset quality and coverage for accurate prompt estimation.

Post Description

Hi, I'm Kamil and I'm a founder of Applied AI agency in Warsaw, Poland.

There is a lot of projects in AI visibility/GEO/AI SEO space. I wanted to see what is really possible in terms of how and when ChatGPT, Gemini, Perplexity, etc. reference certain brands.

Turns out it's all pretty much about reverse engineering the prompts users write because the platforms don't share any analytics as of today.

So I've built a tool that tries to estimate those prompts.

The approach is:

1. Crawl a website and extract its key topics. 2. Analyze organic search keywords and phrases. 3. Find semantically similar conversations in the WildChat dataset (~1M ChatGPT conversations). 4. Generate realistic prompts that users are likely to ask when looking for products or recommendations in that category.

The tool is open source and available on github: https://github.com/syntropicsignal-ai/ai-visibility-audit

I target the tool primarily for e-commerce stores as this seems to be a gap in the market.

I'm curious to hear what you think about this.