Filter and approve UK regulatory news with Google Sheets, Hugging Face, OpenAI, Firecrawl and Jev

by Stephen Anindo ✓ · 20 views · created 2026-09-21 · Market Research, AI RAG

What this workflow does

This workflow has 41 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Google Sheets. It also calls api.openai.com, api.firecrawl.dev and api.typesafe.ai over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).

1. Configure context (Edit Fields (Set)): sets 17 fields: sheetDocumentId, sourceTab, articlesTab…
2. Start fresh this run? (If): checks a condition and branches into true / false
3. Fetch live articles too? (If): checks a condition and branches into true / false
4. Clear previous packages (Google Sheets): clear
5. Continue after clear gate (Merge): merges the data from its input branches
6. Live fetch (FCA Press Release) (RSS Read): reads an RSS feed
7. Clear seen ledger (Google Sheets): clear
8. Read source articles (Google Sheets): uses Google Sheets
9. Read seen ledger (Google Sheets): uses Google Sheets
10. Map live articles to dataset shape (Edit Fields (Set)): sets 7 fields: id, title, summary…

…plus 29 more steps. See the full node list below.

Services it uses

Google Sheets

HTTP calls to: api.openai.com, api.firecrawl.dev, api.typesafe.ai

Before you upgrade to n8n 3.0

Nodes used (14)

• Manual Triggern8n-nodes-base.manualTrigger
• Webhookn8n-nodes-base.webhook
• Edit Fields (Set)n8n-nodes-base.set
• Google Sheetsn8n-nodes-base.googleSheets
• Coden8n-nodes-base.code
• Filtern8n-nodes-base.filter
• Aggregaten8n-nodes-base.aggregate
• Switchn8n-nodes-base.switch
• HTTP Requestn8n-nodes-base.httpRequest
• Ifn8n-nodes-base.if
• Mergen8n-nodes-base.merge
• RSS Readn8n-nodes-base.rssFeedRead
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Waitn8n-nodes-base.wait

From the author

Quick overview This workflow pulls article links from Google Sheets and optional live RSS feeds, filters and deduplicates them using Hugging Face or OpenAI embeddings, then uses Firecrawl plus TypeSafe JEV scoring to approve the most relevant stories and…

View the original on n8n.io → Check your own copy