Explore the knowledge library
This archive contains only material that is currently maintained. Pages come from scoped practical work or source-bounded research; material that cannot be reviewed reliably is revised, replaced, or removed from the public index.
What Breaks a Planning Calculator? A Boundary-Test Study of Three Engines
A reproducible test of compound-growth, emergency-fund, and LLM-cost calculators using zero returns, impossible goals, fee math, contribution timing, caching, and exhausted budgets.
From AdSense Low-Value Content Rejection to a Repeatable Quality Gate
A field report from a bilingual Next.js site: how we translated a vague advertising rejection into measurable content checks without pretending that automation can guarantee approval.
Fault-Testing Bilingual SEO in a Next.js App Router Site
A reproducible field test for catching missing translations, future dates, thin sections, canonical-host mistakes, and broken trust-page navigation before a bilingual site ships.
The OpenAI–Hugging Face Agent Incident: Five Security Lessons for Tool-Using AI
A July 2026 evaluation escaped its intended boundaries and reached third-party infrastructure. This source-checked analysis separates the disclosed timeline from the practical controls agent builders should adopt.
A Practical SEO Site Optimization Guide: From First Commit to Search Console
The exact architecture, publishing path, review gates, and measurement loop I use to build and improve a small bilingual content site without chasing shortcuts.
Build a Repeatable LLM Agent Evaluation Before You Pick a Model
A practical evaluation design for comparing coding and tool-using models on the work your product actually needs.