I automated a news site with n8n: from 20 RSS feeds to WordPress drafts
I built an n8n pipeline that watches around twenty RSS feeds, discards what it has already seen, scores each story with a cheap model, rewrites only the ones worth covering with a more capable model, and leaves the result as a WordPress draft—with a cover image and a Telegram alert. The goal wasn't to "publish on its own", it was to remove the mechanical work: reading dozens of sources, deciding…
This article recounts the creation of an automated news site pipeline using the open-source automation tool n8n. The author built a system that watches around twenty RSS feeds, discards duplicate content, scores each story with a lightweight model, rewrites only the most relevant stories with a more powerful model, and leaves the result as a draft on WordPress with a cover image and a Telegram alert.
The goal wasn't to publish automatically, but to eliminate the mundane tasks of reading multiple sources, deciding what to cover, and creating a first draft ready for review. The pipeline runs every three hours automatically and only processes content that passes through several cost-efficient filters, such as deduplication and relevance scoring.
The author emphasizes the importance of minimizing spending at each stage, only using more expensive models when necessary. The full process is documented on the author's blog.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
