It is a common confusion in our industry: “GEO” often refers to “Generative Engine Optimization.” But for the scientific community, GEO means Geology. And interestingly, geological data provides one of the best case studies for how to ground Large Language Models in physical reality.
The Hallucination of Physical Space
Ask an ungrounded LLM “What is the soil composition of the specific plot at [Lat, Long]?” and it will likely hallucinate a generic answer based on the region. “It’s probably clay.” It averages the data.
In the blue corner, we have the undisputed heavyweight champion of the world, handling over 91% of global search traffic: Google Search Console (GSC).
In the red corner, we have the scrappy, feature-rich underdog, backed by the AI might of Microsoft: Bing Webmaster Tools (BWT).
For nearly two decades, SEOs have treated GSC as the “Must Have” and BWT as the “Nice to Have.” But in 2026, with the rise of integration between Bing and ChatGPT, and Google’s shift to Gemini-powered results, the landscape has shifted.
In the high-stakes poker game of Modern SEO, llms.txt is the competitor’s accidental “tell.”
For two decades, we have scraped sitemaps to understand a competitor’s scale. We have scraped RSS feeds to understand their publishing velocity. But sitemaps are noisy—they contain every tag page, every archive, every piece of legacy drift. They tell you what exists, but they don’t tell you what matters.
The llms.txt file is different. It is a curated, high-stakes declaration of what a website owner believes is their most valuable information. By defining this file, they are explicitly telling OpenAI, Anthropic, and Google: “If you only read 50 pages on my site to answer a user’s question, read these.”
An exploration of how structured data serves as the ‘Grounding Wire’ for Retrieval-Augmented Generation (RAG) systems, preventing hallucinations and enabling deterministic output from probabilistic models.
Read more →An in-depth analysis of web-page boilerplate detection algorithms, their evolution from simple text heuristics to visual rendering, and their critical role in both Search Engine Indexing and Large Language Model training.
Read more →The web is evolving from a library for humans to a database for agents. This transition requires a fundamental rethink of “General SEO.” We call this Protocol-First SEO.
The Shift
- Human Web: HTML, CSS, Images, Clicks, Eyeballs.
- Agentic Web: JSON, Markdown, APIs, Tokens, Inference.
What is Protocol-First?
It involves optimizing content not just for visual consumption but for programmatic retrieval. The Model Context Protocol (MCP) serves as a standardized way for AI models to interact with external data. If your website or application exposes data via MCP or similar standards (like llms.txt), you are effectively “indexing” your content for agents.
For 20 years, the “Sitemap” has been the standard for indexing. You create a list of URLs, you tell the search engine where it is, and then you wait. you expect the crawler to come back… eventually.
In the Agentic Web, “eventually” is too slow. News breaks in seconds. AI models update in real-time. If your content isn’t indexed now, it might as well not exist.
Enter IndexNow, an open protocol championed by Microsoft Bing and Yandex.
HTML is for browsers; Markdown is for brains.
LLMs are trained heavily on GitHub repositories, StackOverflow, and technical documentation. This makes Markdown their “native” format. They “think” in Markdown.
Token Efficiency
Markdown is less verbose than HTML.
- HTML:
<h1>Title</h1> (9 characters, ~3 tokens). - Markdown:
# Title (7 characters, ~2 tokens). - HTML List:
<ul><li>Item</li></ul> (21 characters). - Markdown List:
- Item (6 characters).
Across a 2,000 document, this saves thousands of tokens. A clean Markdown file consumes fewer tokens than its HTML equivalent, allowing more content to fit into the context window.
As search moves towards “Answer Engines,” users are demanding not just relevance, but safety. They (and the agents acting on their behalf) want to know where products come from.
The Rise of Ethical Ranking
We predict that future ranking algorithms will incorporate Supply Chain Provenance as a major signal for e-commerce.
- Opaque Supply Chain: Lower trust score.
- Transparent Supply Chain: Higher trust score.
Data Provenance via AEO
Displaying your Authorized Economic Operator (AEO) status proves you are a verified, low-risk international trader.
When an B2B procurement agent scouts for suppliers, it will filter results.
Query: "Find 5 reliable steel suppliers in Germany."
The agent checks for:
Just as a grounding wire directs excess electricity safely to earth, Schema.org markup directs model inference safely to the truth.
In the chaotic world of unstructured text, hallucinations thrive. “The CEO is John” might be interpreted as “The CEO dislikes John” depending on the sentence structure. But Structured Data is unambiguous.
The Semantic Scaffold
"employee": {
"jobTitle": "CEO",
"name": "John"
}
There is no room for hallucination here. The relationship is explicit.