Author: Artur Ferreira
-
Month 0: Why Every GEO Content Plan Needs a Baseline Before Month 1
Read more →: Month 0: Why Every GEO Content Plan Needs a Baseline Before Month 1Every 12-month GEO content plan assumes a known starting citation rate. Month 0 is five consecutive days of measurement on a fixed query set across three platforms — before any…
-
WordPress wpautop Breaking HTML with Embedded CSS: The Fix
Read more →: WordPress wpautop Breaking HTML with Embedded CSS: The FixWordPress wpautop mangles embedded CSS and HTML structure. The fix: wrap all content in a wp:html block to bypass auto-formatting.
-
From 0 to 71/71: Building a GEO Compliance Audit System
Read more →: From 0 to 71/71: Building a GEO Compliance Audit SystemBuilt a 71-check GEO compliance audit system for WordPress. From zero automated checks to full coverage across schema, structure, and AI readability.
-
E016: The Noise Floor Experiment — What AI Citation Rate Looks Like With No Intervention
Read more →: E016: The Noise Floor Experiment — What AI Citation Rate Looks Like With No InterventionE016 ran the 30-check protocol for five consecutive days with zero content changes. The noise floor is 13.3%–20.0% combined. Perplexity: 40%, zero variance. ChatGPT: 0%–20%. Google AIO: absent.
-
I Read the AGENTS.md Research Paper. Then I Deleted 80% of My CLAUDE.md.
Read more →: I Read the AGENTS.md Research Paper. Then I Deleted 80% of My CLAUDE.md.The AGENTS.md research paper revealed System Memory as the missing GEO Stack layer. Reduced CLAUDE.md by 80% using the four-file pattern.
-
10 RankMath Issues in 9 Days: A Complete Failure Log
Read more →: 10 RankMath Issues in 9 Days: A Complete Failure LogTen RankMath failures in nine days: schema conflicts, TOC crashes, N/A scores, and the first-paragraph trap. Complete failure log with fixes.
-
Log File Analysis as a GEO Instrumentation Layer
Read more →: Log File Analysis as a GEO Instrumentation LayerHow log file analysis measures Googlebot and AI crawler behaviour for GEO experiments — architecture, parity metrics, and anomaly detection in the GEO Lab stack.
-
We Ran a Controlled Entity Density Experiment. Here’s the Null Result and What It Means.
Read more →: We Ran a Controlled Entity Density Experiment. Here’s the Null Result and What It Means.A controlled experiment measuring entity density vs AI citation rate across 10 pages. Result: 0% competition citation rate. Domain authority gates citation eligibility — entity density operates within that gate.
-
Building a Native WP Form to Replace Google Forms
Read more →: Building a Native WP Form to Replace Google FormsGoogle Forms required login for external users. Built a native WordPress form with PHP handler and Google Sheets integration as replacement.
-
The LLM Knowledge Compiler: Beyond Karpathy
Read more →: The LLM Knowledge Compiler: Beyond KarpathyKarpathy described an LLM that compiles raw sources into a wiki. The LLM Knowledge Compiler adds what he left out: a versioned AGENTS.md schema, contamination mitigation, and a spaced repetition…