<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>LLM Cartel Blog</title>
    <subtitle>Field reports from a working GEO agency.</subtitle>
    <link href="https://llmcartel.com/atom.xml" rel="self" type="application/atom+xml"/>
    <link href="https://llmcartel.com/blog" rel="alternate" type="text/html"/>
    <id>https://llmcartel.com/blog</id>
    <updated>2026-06-29T00:00:00Z</updated>
    <author>
        <name>LLM Cartel</name>
        <uri>https://llmcartel.com/about</uri>
    </author>
    <entry>
        <title>Do LLM Bots Actually Use Cloudflare&apos;s Markdown for Agents?</title>
        <link href="https://llmcartel.com/blog/markdown-for-agents" rel="alternate" type="text/html"/>
        <id>https://llmcartel.com/blog/markdown-for-agents</id>
        <updated>2026-06-29T00:00:00Z</updated>
        <published>2026-06-29T00:00:00Z</published>
        <summary>We turned on Cloudflare&apos;s Markdown for Agents on a real high-traffic site and instrumented the edge to find out which AI bots actually request the markdown.</summary>
        <author><name>Patrick Coombe</name></author>
    </entry>
    <entry>
        <title>Do LLM Bots Actually Read JSON-LD, and Will They Cite It?</title>
        <link href="https://llmcartel.com/blog/json-ld-ai-citation" rel="alternate" type="text/html"/>
        <id>https://llmcartel.com/blog/json-ld-ai-citation</id>
        <updated>2026-06-25T00:00:00Z</updated>
        <published>2026-06-25T00:00:00Z</published>
        <summary>A live experiment: we planted a fact only in a page&apos;s JSON-LD and nowhere a human can see it, to test whether AI answer engines ingest and cite structured data.</summary>
        <author><name>Patrick Coombe</name></author>
    </entry>
    <entry>
        <title>Does noindex Keep You Out of AI Answers?</title>
        <link href="https://llmcartel.com/blog/noindex-ai-answers" rel="alternate" type="text/html"/>
        <id>https://llmcartel.com/blog/noindex-ai-answers</id>
        <updated>2026-06-25T00:00:00Z</updated>
        <published>2026-06-25T00:00:00Z</published>
        <summary>A live experiment: a noindexed page, never linked or listed, distributed only by hand off-web, to test whether AI answer engines ingest it anyway.</summary>
        <author><name>Patrick Coombe</name></author>
    </entry>
    <entry>
        <title>GEO Case Study: AI Chatbots Are Really Bad at Reading JavaScript</title>
        <link href="https://llmcartel.com/blog/geo-case-study-ai-chatbot-javascript" rel="alternate" type="text/html"/>
        <id>https://llmcartel.com/blog/geo-case-study-ai-chatbot-javascript</id>
        <updated>2026-05-19T00:00:00Z</updated>
        <published>2026-05-19T00:00:00Z</published>
        <summary>We logged what ChatGPT, Claude, Gemini, Grok and Perplexity actually fetch when you paste them a URL. Every one is JavaScript-blind - server-side proof for GEO and AEO.</summary>
        <author><name>Patrick Coombe</name></author>
    </entry>
    <entry>
        <title>How Long Does It Take an LLM Bot to Discover a New Business Entity?</title>
        <link href="https://llmcartel.com/blog/llm-bot-discovery-case-study" rel="alternate" type="text/html"/>
        <id>https://llmcartel.com/blog/llm-bot-discovery-case-study</id>
        <updated>2026-05-08T00:00:00Z</updated>
        <published>2026-05-08T00:00:00Z</published>
        <summary>We turned llmcartel.com into a clean-slate experiment to measure how long LLM bots take to discover a new business. Setup, the day-zero gotcha, and the live crawl log.</summary>
        <author><name>Patrick Coombe</name></author>
    </entry>
</feed>
