Build an AI Automation with an RSS Trigger in n8n
Most n8n + AI tutorials end with a workflow that works once. This one is built to keep running: it triggers on an RSS feed, summarizes new items with an LLM, filters out noise, and posts to Slack. It also covers what happens when things fail. The workflow RSS Feed Trigger → Basic LLM Chain (Claude) → Code (validate JSON) → IF (relevance) → Slack Plus a separate Error Workflow for alerts. Do you…
This tutorial guides readers through creating an n8n workflow that automates AI summarization of RSS feed items and posts summaries to Slack when relevant. The workflow starts with an RSS Feed Trigger node, which polls the feed every 30 minutes, ensuring deduplication since RSS has no webhooks. Next, an LLM summarization step with Anthropic's Chat Model is added, capping token costs per item using .slice(0, 6000).
Validation of LLM output occurs in a Code node, ensuring JSON structure and required fields before proceeding. An IF node with a relevance threshold of 6 filters out low-quality summaries. Finally, a Slack node delivers formatted summaries, including title, link, relevance score, and tags. The tutorial also highlights error handling mechanisms, including a dedicated Error workflow for alerts and workarounds for Slack downtime.
Optional enhancements include sending alerts via email or Notion, merging multiple feeds, or adding human approval steps before publishing.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
