Automating Morning Digests: n8n Pipeline Architecture for News Filtering
Problem Three centuries ago, traders read newspapers to make decisions. Today — RSS feeds, Twitter, Telegram channels, news aggregators. The volume of data outpaces human capacity to process it. Manual search, verifica
Problem
Three centuries ago, traders read newspapers to make decisions. Today — RSS feeds, Twitter, Telegram channels, news aggregators. The volume of data outpaces human capacity to process it. Manual search, verification, and digest creation can consume up to half a workday.
Solution
Content Forge is an n8n-based pipeline that collects news from three RSS sources (CoinTelegraph, The Block, Decrypt), filters by keywords, and creates GitHub Issues with the two most relevant articles.
Previously, manual digest creation consumed half a workday. After the pipeline was implemented, reviewing a ready-made summary takes 2–3 minutes. The savings amount to 4–5 hours per day.
Implementation
The pipeline consists of four stages. RSS nodes pull feeds from three sources. The Merge node combines streams. Filter selects articles by keywords and limits results to two articles. GitHub Issues are created automatically with titles containing keywords from the RSS source.
Each created Issue becomes an SEO indexing point. When a blog article is published based on an Issue, it gets indexed by search engines for keywords from the title. Content Forge works as an SEO magnet, identifying emerging topics before publication.
The pipeline is not topic-specific — it processes any RSS format. Adding a new source requires creating a new RSS node and connecting it to Merge.
A detailed breakdown of filter configuration and deduplication will follow in future publications.
Resources
Originally published by Dev.to WebDev. Aggregated on AIWithGhost for educational purposes — full credit and traffic to the original publisher.