I built a 2,000-page, four-language website with AI. Google sends it two people a day

The creator of artatlas.site shares their experience building a large-scale art history encyclopedia using the AI tool Claude Code. The site contains over 2,000 HTML pages in four languages, covering 184 paintings and 107 artists. Despite technical optimization, high Lighthouse scores, and valid JSON-LD markup, the project faces low traffic, with Google bringing an average of only 1.9 visitors per day. In the article, the author analyzes the reasons for this failure, detailing the development process, the challenges of working with AI, and the disappointment regarding the SEO performance of AI-generated content. This case study raises important questions about the quality of automated content and how it is perceived by search algorithms in the current digital landscape.
This is a summary. Read the full article at the original source:
HabrRelated stories
Why I run smoke tests directly in production and how they once broke my analytics
In this article, the author explores the practice of running automated smoke tests directly in a production environment. The focus is on using synthet…
How Sanity Context & MCP Supercharged AI Customer Support in Basegent & Bucket Space
Developer Miracle Onyenma details the architecture behind Basegent, an AI-driven customer support platform integrated with Sanity Context. Moving beyo…
Vincent Bernat explores a robust, self-hosted approach to creating HTTP tunnels using standard SSH and Nginx configurations. Rather than relying on th…



