I have been designing for banks for over 10 years. Now I build everything from scratch with Claude, Midjourney, and PHP. This is not theory. It is what I do every day.
What this is
A trilingual technical blog about AI, GEO and UX design. I document what I build, what fails, and what I measure. No generic theory.
Who it is for
Developers, designers and SEOs who want to optimize their content for AI agents, not just Google.
Google Search says you do not need llms.txt for AI visibility. Google Chrome now audits whether your site has one. Two teams, two positions, one company. I have had mine live for 5 months.
Every image on this blog is automatically generated from the article text. No stock photos, no DALL-E, no Midjourney. The system reads the content, extracts patterns, and produces images unique to each post. It's generative design applied to brand identity. Here's how it works.
In March 2026 my blog had DA 14 and 206 monthly users. I decided to stop optimizing for Google rankings and start optimizing for AI citations. Four months later, here are the numbers. Some confirmed my thesis. Others surprised me.
agent-permissions.json says what an agent can do on your site. agents.json goes further: it describes exactly how to do it. It's a formal contract between your site and the agents that visit it. I implemented it on my blog and this is what I learned.
Traditional SEO optimizes for Google to index you. GEO optimizes for AI to cite you. Agentic SEO is the next step: optimizing so AI agents don't just read your content but use your tools. I already implemented it. Here's how.
My blog already serves Markdown to AI agents and HTML to humans. The next step went further: adapting content sections based on reader type. No JavaScript frameworks. No machine learning. Just PHP, conditional logic, and browser signals.
A new standard proposes that websites explicitly declare what AI agents can and cannot do on their pages. I implemented it on my blog with vanilla PHP. Here's the code, the decisions I made, and why this will matter more than robots.txt.
80% of your users are not browsing next to a router. Testing your website on mobile WiFi hides the real performance problems your users face every day on mobile data, low signal, and unstable connections.
Complete technical guide on how I implemented Generative Engine Optimization on a PHP blog from scratch. Real code for llms.txt, semantic JSON-LD with automatic Knowledge Graph, and the content structure that makes LLMs cite you.
I stopped designing for screens and started designing for machines that think. GEO, custom Knowledge Graphs, and Sentiment Mapping are concepts that 90% of developers still do not master.