---
id: "prereq-llm-architecture"
type: "prereq"
source_timestamps: ["§ How to increase brand awareness on LLMs", "§ How to Market to LLMs"]
source_url: "https://hbr.org/2025/06/forget-what-you-know-about-seo-heres-how-to-optimize-your-brand-for-llms"
source_title: "Forget What You Know About Search. Optimize Your Brand for LLMs."
tags: ["technical-literacy"]
related: ["action-provide-proof-of-expertise", "question-technical-ingestion-mechanics"]
reason: "Required to execute the technical implementation of 'structured digital storytelling' and trust signals."
sources: ["geo"]
sourceVaultSlug: "hbr-seg-geo"
originDay: 3
articleStem: "hbr-ext-10-optimize-brand-for-llms"
sourceUrl: "https://hbr.org/2025/06/forget-what-you-know-about-seo-heres-how-to-optimize-your-brand-for-llms"
sourceTitle: "Forget What You Know About Search. Optimize Your Brand for LLMs."
---
# Basic understanding of LLM data ingestion

While the article does not detail Retrieval-Augmented Generation (RAG) or web-scraping mechanics, its advice to use **'structured data,' 'tables,' and 'links to PubMed'** assumes the reader understands that LLMs **ingest, parse, and weight structured digital text differently than human readers**.

**Why it's required:** to execute the technical implementation of 'structured digital storytelling' and [[action-provide-proof-of-expertise|trust signals]].

**Enrichment (fills the gap the article leaves):** Key adjacent concepts an implementer needs — **RAG** (models retrieve documents from specific indexes/corpora before generating), **schema.org markup** and **llms.txt** files (signal to AI crawlers what content to ingest and how), and the reality that visibility can depend on **curated corpora and data partnerships**, not just open-web content. This connects directly to the unresolved [[question-technical-ingestion-mechanics]].


## Related across articles
- [[prereq-llm-rag-mechanics]]
- [[prereq-llm-parsing]]
- [[prereq-llm-mechanics-d3]]