DEV Community

AI ZALO
AI ZALO

Posted on

GEO-62: An Open Diagnostic Standard for Technical SEO, AEO & Generative Engine Optimization (RFC 9727 + llms.txt)

#webdev #seo #ai #opensource

As AI Search engines (Google AI Overviews, Google AI Mode, Perplexity, ChatGPT Search, and Claude) shift user discovery from traditional ten-blue-links to Retrieval-Augmented Generation (RAG) synthesis, traditional SEO linters miss critical machine-readability signals: RFC 9727 API Catalog headers (Link: </.well-known/api-catalog>), llms.txt discovery, AI Crawler robots.txt governance, Answer-First opening blocks, and typed semantic E-E-A-T verification.

To solve this deterministically at the Cloudflare Edge, we built AEORank (Vietnamese Edition) and released the open GEO-62 Diagnostic Standard archived on CERN Zenodo (DOI: 10.5281/zenodo.23582947) and Hugging Face.

1. Architecture of a Deterministic + Typed-Semantic GEO Audit

Most SEO tools either rely on superficial regex checks or ask a generic LLM to "score this page from 1 to 100" (producing non-reproducible hallucinations). AEORank separates the diagnostic pipeline into four strict layers:

  1. 56 Single-Page + 6 Multi-Page Sitemap Deterministic Checks (GEO-62): Evaluates HTTP headers, canonicals, hreflang reciprocity, JSON-LD sameAs entity graphs, Core Web Vitals, llms.txt, and RFC 9727 (/.well-known/api-catalog).
  2. Typed Probabilistic Semantic Engine (AEO-Sem): Evaluates 13 page-level and 5 site-level binary propositions (such as jev_answer_first, jev_trust, and jev_entity_clarity) using calibrated logprob thresholds (p >= 0.80).
  3. Live Multi-Engine AI Citation Verification: Queries Perplexity and Google AI Mode in real time to verify whether the target domain is actively cited for its primary entity queries.
  4. Weekly Drift Guard: Automatically monitors score regressions across deployed production sites.

2. Why Answer-First & First-4,000-Char E-E-A-T Placement Matter for RAG

When an AI Search retriever chunks a webpage, boilerplate navigation or buried definitions cause the RAG reranker to drop the passage. In AEORank's Knowledge Base, two high-impact semantic checks govern RAG extraction:

  • Answer-First Opening (JEV-AF): The first 500 characters immediately following <h1> (and the first two sentences under each <h2>) must directly define and answer the core query before elaborating.
  • Early E-E-A-T & Entity Provenance (JEV-TRUST): Verifiable credentials, methodology, and sameAs links to authoritative registries (GitHub, CERN Zenodo DOI, Hugging Face, Wikidata) should appear within the first 4,000 characters of the document body and inside the <script type="application/ld+json"> graph.

3. Open Specification, Dataset & Edge API

We have published the complete GEO-62 Rule Index and OpenAPI 3.0.3 specification across open registries for developers and autonomous AI agents:

You can inspect the public rule index directly via curl:

curl -s https://aeorank.app/api/v1/rules | jq '.counts'
Enter fullscreen mode Exit fullscreen mode

Top comments (0)