Everything you should know about Query Fan Out From the Guy that Made the First Tool for QFO and made it open source, but none of the Major SEO software companies have one yet, wtf

[00:00] – Intro, context for the day (query fanout + Mike’s “chunks” post), housekeeping

[01:08] – Mike’s intro + why Query Fanout matters now

[02:11] – “I told you so”: SGE/RAGGLE origin story + early AI Overviews replication

[03:31] – CTR loss predictions + what Mike originally got wrong

[04:40] – Query Fanout defined: synthetic sub-queries, raffle-ticket visibility model

[06:31] – What the data says: Google↔AI overlap, position bias, diminishing returns, fanout size/length

[09:56] – How it works under the hood: RAG pipeline + orchestration + hybrid retrieval

[12:31] – Query expansion types: intent classification, slots, latent intent, rewrites, speculative questions

[14:51] – Routing + cost-to-retrieve + content-type eligibility (why “only articles” breaks)

[16:33] – Where fanout data comes from: ChatGPT metadata endpoints + Gemini API proxy
[19:01] – Qforia walkthrough: patents → query types → reverse intersect + “chunk daily” feedback loop

[24:05] – Tooling landscape: DemandSphere, PromptWatch, Profound, Market Brew + caching behavior

[26:45] – Relevance Engineering playbook: audits, embeddings, ecosystem signals, structured data, 499/page speed

[31:04] – Writing for synthesis: chunk sizing, headings, semantic triples, specificity + simulation/testing

[35:52] – Filling SEO tooling gaps yourself: n8n, Ollama + Screaming Frog, crew.ai agents

[39:59] – Wrap: five takeaways + resources (AI Search Manual, Q4E, SEO Week)

[41:10] – Q&A: snippets vs meta descriptions, embeddings choices, personalization impact, APIs vs UI scraping, hallucinations, indexing, content strategy going forward