A few interesting technical challenges:

PATTERN-BASED IMAGE GENERATION Generic AI images all look the same ("holographic businessman with laptop"). I solved this with a JSON database of 60+ concrete visual patterns—context-aware selection prevents repetition. Funding news → coins/contracts, security → locks/shields. Much more visual diversity. Still needs tweaking though.

GRADUAL SITEMAP GROWTH FOR NEW SITES Daily news pipeline generates lots of content. Challenge: Google indexes new sites slowly—exposing all 2K+ URLs at once resulted in 1-3% indexing rate. Solution: Dynamic rolling window in sitemap—only expose top 50 most recent articles (300 URLs), gradually increasing to 100 → 150 → 200 over 6 months as site builds authority. Result: Indexing rate improved to 10%.

AUTOMATED TRANSLATION PIPELINE RSS aggregation → AI summaries and translation with context-aware prompts → human review queue. Still tweaking quality per language pair.

STACK: Next.js 15 with Turbopack, PostgreSQL, deployed via Sliplane@Hetzner which works pretty ok.

STATUS: 1+ month post launch, 80 pages indexed, 100+ European apps featured (Mollie, Wire, Ecosia, LanguageTool, etc.)

FEEDBACK WELCOME ON: • European news sources I'm missing? • Better approaches to multilingual SEO? • Translation quality red flags? • How to optimize for LLM discovery (ChatGPT, Claude, etc.)?

Take this[0],

DATENSCUNTZ-EINSTELLUNES should be DATENSCHUTZ-EINSTELLUNGEN

ALLE AKZIETTREN should be ALLE AKZEPTIEREN

you get the point, basically almost all the text is wrong...i think AI-generated images are annoying and vapid enough, but if they don't even show actual text then what's the point? the english ones seem to be fine, can't judge the spanish ones. images feel like a lazy business-powerpoint.

anyways, cool site in general :)

[0]https://europedigital.cloud/_next/image?url=%2Fapi%2Fnews-im...

I suggest posting this in Show HN [1] if your server can handle it.

[1] https://news.ycombinator.com/show