Track documentation changes with Firecrawl, Postgres, Gemini, and Telegram
UnknownWhat this workflow does
This AI workflow has 13 nodes and runs on a schedule (cron 0 9 * * *). Along the way it connects Postgres, Google Gemini, Telegram and Firecrawl V2 (community).
How it runs
Trigger: On a schedule (cron 0 9 * * *).
- Firecrawl: map
- Split & Filter Links (Code): runs custom JavaScript code
- Firecrawl: uses Firecrawl
- Hash Content (Code): runs custom JavaScript code
- Postgres: run a query
- Filter: keeps only the items that match a condition
- Aggregate: combines items into one
- If: checks a condition and branches into true / false
- Format Changes List (Code): runs custom JavaScript code
- Gemini Summarize Changes (Google Gemini): uses Google Gemini
…plus 1 more step. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-firecrawl-v2 is verified or supports 3.0 (used in Firecrawl Map Docs, Firecrawl Scrape Page).
Nodes used (10)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Firecrawl
n8n-nodes-firecrawl-v2.firecrawl - Code
n8n-nodes-base.code - Postgres
n8n-nodes-base.postgres - Filter
n8n-nodes-base.filter - Aggregate
n8n-nodes-base.aggregate - If
n8n-nodes-base.if - Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - Telegram
n8n-nodes-base.telegram - No Operation, do nothing
n8n-nodes-base.noOp
From the author
This template watches an external documentation site every day and sends an AI-generated Vietnamese summary to Telegram whenever pages change. It is built around Postgres content hashing so it works with any Firecrawl deployment (Cloud or self-hosted) and any…