llms.txt Content
# Metehan Yesilyurt — metehan.ai
> AI Search and SEO researcher. Publishing original research on LLM visibility, AI-powered search engines, and the next era of discoverability.
## Links
- Website: https://metehan.ai
- X: https://x.com/metehan777
- LinkedIn: https://www.linkedin.com/in/metehanyesilyurt
- GitHub: https://github.com/metehan777
- Substack: https://metehanai.substack.com
- RSS: https://metehan.ai/rss.xml
- Sitemap: https://metehan.ai/sitemap-index.xml
- llms-full.txt: https://metehan.ai/llms-full.txt
## Topics
- AI Search & LLM Visibility (AEO / GEO)
- Google Discover Architecture
- Screaming Frog AI Integrations
- MCP Servers for SEO Tools
- Tokenizer & Embedding Research
- Search Algorithm Reverse-Engineering
## Articles (173)
- [How I Turned Meta AI's Brain Scanner Model Into a Free SEO Tool](https://metehan.ai/blog/how-i-turned-meta-ais-brain-scanner-model-into-a-free-seo-tool/): I took Meta AI's TRIBE v2 model and turned it into a free SEO analysis tool. TRIBE v2 was trained on 1,115 hours of real fMRI brain recordings from over 700 humans.
- [I Turned 16 Months of Google Search Console Data Into a Vector Database. Here's What I Learned.](https://metehan.ai/blog/i-turned-16-months-of-google-search-console-data-into-a-vector-database-heres-what-i-learned/): I had a simple question: what if I could talk to my search performance data instead of staring at charts in Google Search Console?
- [I Built a 60,000-Page AI Website for $10: GPTBot Crawled It 30,000+ Times in 12 Hours](https://metehan.ai/blog/i-built-a-60-000-page-ai-website-for-10-gptbot-crawled-it-30-000-times-in-12-hours/): Let me be clear upfront: this website is designed purely as an experiment. I wanted to observe what real traffic looks like on a large-scale programmatic SEO site and more importantly, how AI crawlers behave in the wild.
- [Google Discover Architecture: Clusters, Classifiers, OG Tags, NAIADES - What SDK Telemetry Reveals](https://metehan.ai/blog/google-discover-ar