DEV Community: AI ZALO

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

AI ZALO — Fri, 23 Oct 2026 02:15:37 +0000

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:

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).
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).
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.
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:

Live Diagnostic Platform (English): https://aeorank.app/
Live Diagnostic Platform (Vietnamese): https://aeorank.app/vi/
GEO-62 Engineering Knowledge Base: https://aeorank.app/learn
CERN Zenodo Technical Note & DOI: https://doi.org/10.5281/zenodo.23582947 (Record #23582947)
Hugging Face Open Dataset: https://huggingface.co/datasets/lekhoa288/aeorank-geo62-diagnostic-standard
GitHub Open Specification Repo: https://github.com/aizaloapp/aeorank & GitHub Pages Portal
ClawHub AI Agent Skill: https://clawhub.ai/aizaloapp/skills/aeorank-seo-geo-auditor

You can inspect the public rule index directly via curl:

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

Building a Zero-Server 3D Pickleball Biomechanics & MediaPipe Pose Coach on the Edge (WebGL + MCP)

AI ZALO — Fri, 23 Oct 2026 02:14:06 +0000

When recreational Pickleball players (DUPR 2.0–3.5) struggle with popping up balls at the Non-Volley Zone (Kitchen) or develop Pickleball Elbow, the root cause is almost always biomechanical: generating force by snapping the wrist instead of sequencing the kinetic chain from knee bend to hip-shoulder separation.

Instead of relying on static 2D coaching videos or uploading private user videos to expensive cloud GPU servers, our engineering team built PickleBase (Vietnamese Edition) — a client-side 3D Pickleball biomechanics simulator, interactive tactical board, and MediaPipe Pose WebGL video analyzer backed by an open-standard Model Context Protocol (MCP) server at the edge.

In this engineering deep dive, we break down the client-side 3D kinematic math, the interactive court simulator, and our newly released Open Biomechanics Dataset archived on CERN Zenodo (DOI: 10.5281/zenodo.23582848) and Hugging Face.

1. Zero-Server Pose Tracking Architecture (WebAssembly + WebGL)

When building the PickleBase AI Video Biomechanics Coach, uploading 60fps swing videos to a cloud backend introduced unacceptable latency and privacy concerns. By running MediaPipe Pose Landmarker directly in the browser via WebAssembly and WebGL delegates, we extract 33 3D skeletal landmarks (x, y, z, visibility) at real-time frame rates with zero server GPU cost:

[User 60fps Video / Webcam Stream]
       │
       ▼
[MediaPipe Pose Landmarker (Client-Side WASM + WebGL)]
       │  (Extracts 33 3D skeletal landmarks in normalized space)
       ▼
[3D Vector Kinematic Engine]
       │  ├── Elbow Flexion Stability (Shoulder–Elbow–Wrist angle)
       │  ├── Hip–Shoulder Separation & Torso Rotation
       │  └── Center-of-Gravity height relative to the Non-Volley Zone
       ▼
[Real-Time Fault Diagnostics + 3D Court Trajectory Comparison]

2. Computing 3D Joint Angles from MediaPipe Landmarks

Given three consecutive 3D skeletal landmarks $A(x_1, y_1, z_1)$ (e.g., LEFT_SHOULDER), $B(x_2, y_2, z_2)$ (LEFT_ELBOW), and $C(x_3, y_3, z_3)$ (LEFT_WRIST), the joint angle at vertex $B$ is computed via the 3D dot product of vectors $\vec{BA}$ and $\vec{BC}$:

/**
 * Compute the 3D interior joint angle (in degrees) at vertex B
 * Used in the PickleBase AI Coach engine: https://picklebase.app/ai-coach
 */
export function computeJointAngle3D(a, b, c) {
  const v1 = { x: a.x - b.x, y: a.y - b.y, z: (a.z || 0) - (b.z || 0) };
  const v2 = { x: c.x - b.x, y: c.y - b.y, z: (c.z || 0) - (b.z || 0) };

  const dot = v1.x * v2.x + v1.y * v2.y + v1.z * v2.z;
  const mag1 = Math.hypot(v1.x, v1.y, v1.z);
  const mag2 = Math.hypot(v2.x, v2.y, v2.z);

  if (mag1 === 0 || mag2 === 0) return 0;
  const cosTheta = Math.max(-1, Math.min(1, dot / (mag1 * mag2)));
  return Math.round((Math.acos(cosTheta) * 180) / Math.PI);
}

Key Biomechanical Thresholds Across Core Shots

In our standardized 12-technique dataset published on CERN Zenodo (#23582848) and Hugging Face Datasets, each shot is decomposed into four deterministic phases (Preparation, Kinetic Chain, Contact Point, Follow-Through):

Shot / Technique	Target Kinematic Profile	Common Amateur Fault Detected
Forehand & Backhand Dink	Stable elbow angle (`105°–125°`), locked wrist, lift generated from shoulder pendulum and knee bend	Wrist flicking ($\Delta \theta_{\text{wrist}} > 25^\circ$) causing high pop-ups at the Kitchen line
Third Shot Drop	Contact `20–30 cm` in front of the lead hip, open paddle face (`35°–45°`), apex peaking over the net	Chopping downward like a table tennis cut or contacting behind the hip
Overhead Smash & Erne	Pronounced hip-shoulder separation prior to upward extension; controlled landing outside the $7\text{ ft}$ NVZ	Momentum carrying the player's foot onto the Non-Volley Zone line after the ball is dead (Rule 9 fault)

3. Interactive 3D Tactical Board & USA Pickleball 2026 Rulebook

Doubles Pickleball is won through synchronized court geometry (Stacking, Shading, and coordinated transition from the baseline to the Non-Volley Zone). On the PickleBase 3D Tactical Board and USA Pickleball 2026 Rulebook Hub, players can rotate a full $20 \times 44\text{ ft}$ 3D court to inspect player positioning, coverage cones, and official fault rulings.

4. Open Specification & Edge MCP Server for AI Agents

To make sports biomechanics and official USA Pickleball rules deterministically accessible to AI coding agents and researchers without hallucination, we released the complete specification across open registries:

Interactive 3D Platform (English): https://picklebase.app/en/
Interactive 3D Platform (Vietnamese): https://picklebase.app/
CERN Zenodo Technical Note & DOI: https://doi.org/10.5281/zenodo.23582848 (Record #23582848)
Hugging Face Open Dataset: https://huggingface.co/datasets/lekhoa288/picklebase-open-biomechanics
GitHub Open Specification Repo: https://github.com/aizaloapp/picklebase-open-spec & GitHub Pages Portal
ClawHub AI Agent Skill: https://clawhub.ai/aizaloapp/skills/picklebase-biomechanics-coach
Live Edge MCP & OpenAPI 3.1 Endpoint: https://picklebase.app/api/mcp | https://picklebase.app/openapi.json

You can query the live PickleBase MCP server directly from your terminal:

curl -X POST https://picklebase.app/api/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_technique_biomechanics","arguments":{"technique_id":"third-shot-drop"}}}'

We would love feedback from fellow web graphics, computer vision, and sports-tech engineers!