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

Estimating what users ask ChatGPT about your company

Name: Estimating what users ask ChatGPT about your company
Availability: InStock
Author: biduskamil

by biduskamil·Jun 24, 2026·2 points·1 comment

Visit Project View on HN

AI Analysis

●●●BangerZero to OneBig BrainDark Horse

WildChat dataset reverse-engineers what users ask AI about your brand versus competitors.

Strengths

•Novel methodology combining web crawling, keyword analysis, and conversation mining.
•Self-hosted Docker setup with sample dataset for immediate exploration.
•Produces client-ready PDF reports with competitor share and prioritized recommendations.

Weaknesses

•WildChat dataset coverage may not represent all AI assistant conversations accurately.
•AI visibility tracking is emerging—methodology validation needs more real-world testing.

Post Description

OpenAI, Google and Perplexity don't expose user query analytics. It's difficult to tell if and why your company appears in chat responses.

Turns out the only way you find out currently if you're cited at scale is if you reverse engineer the prompts users might be asking about your brand and track ChatGPT/Gemini/etc. responses for them.

I've built a pipeline, that:

1. crawls your website and your competition

2. analyzes top search keywords from search engines

3. retrieves similar conversations from WildChat (~1M ChatGPT conversations)

4. generates most likely user prompts for your brand.

The result is a set of prompts that users are likely to ask about your company or your products and tracking them shows where LLMs suggest you and where do they reference your competition.

Repo:

https://github.com/syntropicsignal-ai/ai-visibility-audit

I'd love feedback on:

- whether this methodology makes sense

- alternative datasets to WildChat

- better ways to estimate prompt distributions