ChatGPT 5.3/5.4 Query Fan Out Extraction Bookmarklet

AI Summary

This post introduces a free browser bookmarklet designed to extract query fan-out data from ChatGPT without needing an OpenAI API key. Quentin Yacoub explains how this tool reveals the hidden search queries and citations used by the AI, providing SEO/GEO specialists with critical visibility into how LLMs research topics, rank sources, and identify content gaps.

Quentin Yacoub
Quentin Yacoub
5 min
Table of Contents
Blueprint-style graphic featuring the text CHATGPT FAN OUT QUERY EXTRACTION BOOKMARKLET on a grid background.

Cet article est aussi disponible en français : Script d'extraction de query fan-out - ChatGPT 5.3/5.4

This morning I saw a post from Chris Long on LinkedIn mentioning that ChatGPT “Fan Out” is back, and I created a simple bookmarklet to pull this data out. No API keys, no complex setup: just a shortcut in your browser.

I had originally used a bookmarklet from SEO Pub and I remember how helpful it was to quickly check a prompt when I wasn’t working at Adobe. While it is now much easier for me to do this at scale with LLM Optimizer, I wanted to share a simple way for people who don’t have access to those enterprise-level tools.

If you want to do this at scale and for other LLMs as well, feel free to contact me on LinkedIn to discuss how LLM Optimizer could help you.

What is “Query Fan-out”?

When you give ChatGPT a prompt, sometimes it uses RAG (Retrieval-Augmented Generation) and it breaks it down into several specific searches to get the best data before answering you. For example, a prompt like “Best GEO agencies in Montreal” might trigger five different searches for specific agency names, reviews, or local rankings.

We usually only see the final “Sources” list, but the fan-out queries are the breadcrumbs the AI followed to get there.

What the bookmarklet does

This tool uses your existing logged-in browser session to load the same conversation JSON the web app uses. It does not require an OpenAI API key; it simply performs the same class of request you can inspect yourself in your browser’s DevTools.

Once you click it on a conversation page, it opens a new tab where it organizes all the hidden technical data into a readable format.

What It Retrieves

The bookmarklet extracts several key layers of data that are usually hidden in the UI:

  • Fan-out search queries: The actual strings ChatGPT typed into a search engine.
  • Detailed citations: Every URL cited in the response.
  • Web search result snippets: The short page titles and excerpts the AI reviewed for each search hit.

Why It’s Important to Know ChatGPT “Thoughts”

If you are working in SEO/GEO, seeing this information is crucial for a few simple reasons:

  • Organic Ranking Visibility: You can see if your site actually appeared in the search results ChatGPT looked at.
  • Source Tracking: You can see which sites the AI is actually relying on to form its opinion of your industry.
  • Content Gaps: If the AI is searching for “Pricing for [Your Brand]” and finding nothing, you know what content you need to create.

How to Install the Bookmarklet on Chrome

This works for Google Chrome on desktop.

  1. Show your bookmarks bar: Use Ctrl + Shift + B (Windows) or ⌘ + Shift + B (macOS).
  2. Create a new bookmarklet: Right-click an empty area of the bar and choose Add page….
  3. Name it: Call it something like ChatGPT Fan-out.
  4. Paste the script: In the URL field, paste the entire code block below. It must start with javascript:. Chrome bookmarklet dialog: name “ChatGPT Fan-out”, URL field with javascript: bookmark
  5. Run the shortcut: Click the shortcut while on a ChatGPT tab (you must be logged in). ChatGPT conversation open in the browser with the fan-out bookmarklet on the bookmarks bar
  6. Check out the result: A new tab will open displaying all the extracted data. New tab showing extracted fan-out queries, citations, and web search rows from ChatGPT

The Bookmarklet Code

I know we probably haven’t met yet, and I’ll be the first to admit that pasting a block of code into your browser can feel a little sketchy—it definitely did for me the first time.

If you want a second opinion, feel free to paste the code into your favorite LLM and ask: Does this code contain anything malicious, and can the author access my ChatGPT conversations? It’s a great way to verify everything for yourself. This script runs entirely on the page origin (chatgpt.com), uses your existing session, and never sends data to external servers.

I also follow a strict privacy-first approach and do not use tracking cookies, which is why you won’t see a cookie banner on my site. You can read my privacy policy for full details.

Potential Errors

The script might return two types of alerts based on your current session:

  1. No conversation ID in the address bar (/c/...). This means the script can’t find a specific chat to pull data from.
  • Solution: Ensure you are on an active ChatGPT conversation page (the URL should contain /c/ followed by a string of characters). If you are on the homepage, start a chat first or refresh the page.
  1. Nothing to export from this conversation... This occurs when the specific response you are viewing didn’t trigger a web search or use citations.
  • Solution: Try a prompt that forces ChatGPT to look for external data. For example: What are the best Generative Engine Optimization strategies for 2026?

I have only encountered these two scenarios so far. If you run into any other issues, feel free to reach out on LinkedIn and I will update this list for the community. Since becoming a dad back in December, my time for troubleshooting is a bit more limited, but I’ll do my best to help you get it running.

Please note: All opinions and blog posts shared on this website are strictly my own personal projects. They do not represent the views, strategies, or official products of my employer, Adobe.

Quentin Yacoub
Quentin Yacoub
SEO & GEO Specialist

Hi, I'm Quentin, an SEO/GEO Specialist at Adobe building AI powered tools for Site Optimizer and LLM Optimizer. I use this site to document my thoughts on where search is heading in the age of AI, and to share the strategies and shortcuts I rely on.

Connect on LinkedIn

Related Articles

What is AEM Sites Optimizer?

Go behind the scenes of AEM Sites Optimizer to see how we are building an autonomous site optimization system at Adobe.

6 min read

Hello World: My First Website

Welcome to my personal blog. Discover why I built this sandbox to document my experiments in SEO, GEO, and AI-driven search. Here's what to expect.

8 min read