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.
The principle
No stock photos, no generic prompts. Everything built, tested, and documented with Claude and PHP in real production.
Most connected
What is llms.txt and how I implemented it on my blog
The llms.txt file is the equivalent of robots.txt for artificial intelligence. Here is how I built mine and validated i…
14 connections
Explore
My Real Workflow: 4 AIs I Use Every Day as a Designer
How I use 4 AIs every day as a UX/UI designer: Claude for code, Midjourney for images, ChatGPT for ideas and Gemini for…
11 connections
Build
How to write AI prompts: a designer's guide (2026)
What is a prompt, how to write prompts for Midjourney and ChatGPT, and why designers have an advantage writing AI promp…
10 connections
Four AIs read the same llms.txt and all four correctly identified me as a UX/UI designer with fintech experience. In the previous test, using compressed memories, two of them got my profession wrong. A plain text file communicates who I am more clearly than months of conversations.
I asked Claude, ChatGPT, Gemini, and Perplexity to predict my answers to 10 questions. All four built a more rigid, more principled, and more consistent version than the real me. And that version gives worse advice.
I asked Claude, ChatGPT, Gemini, and Perplexity to tell me everything they know about me without searching past conversations. Four different profiles. Four levels of detail. None could tell me which conversation they learned each fact from.
I gave the same URL and the same prompt to GPT, Perplexity, Kimi, Meta AI, and Mistral. Four accessed the real data. One fabricated methods, IDs, and structures that do not exist. And every single one requires registration to use.
I asked ChatGPT, Perplexity, and Gemini to audit 4 pages of shinobis.com without mercy. GPT gave the homepage 6.2. Perplexity and Gemini gave it 4. Here is what they found, what I implemented, and what I discarded.
Every line of PHP on my blog was written with Claude. Three of the bugs it introduced taught me things about PHP I would not have learned otherwise. The require_once that executed code, the duplicated function across sessions, and the echo before header.
I asked Gemini, ChatGPT, and Perplexity to audit the same JSON-LD schema. Gemini gave 9/10. ChatGPT gave 8.2/10. Perplexity gave 7.5/10. Here is what I implemented, what I discarded, and why.
I published a PHP tutorial on freeCodeCamp. The editorial process forced me to understand every function I had built with Claude. I came out of it a better developer.
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.