Recover lost backlinks with DataForSEO, OpenAI, Google Sheets, and Slack
Ready for 3.0What this workflow does
This AI workflow has 22 nodes and runs on a schedule (every week at 08:00) (plus 2 other triggers). Along the way it connects OpenAI Chat Model, Google Sheets and Slack. It also calls api.dataforseo.com over HTTP.
How it runs
Trigger: On a schedule (every week at 08:00) (plus 2 other triggers).
- Settings (Edit Fields (Set)): sets 7 fields: domain, lost_since_days, min_rank…
- Say It Broke (Slack): post (message)
- Ask What We Lost (HTTP Request): calls api.dataforseo.com (POST)
- Read The Lost Links (Code): runs custom JavaScript code
- Read What We Reported (Data table): get
- Drop The Ones We Sent (Code): runs custom JavaScript code
- Anything New To Work? (If): checks a condition and branches into true / false
- One Link Per Loss (Split Out): splits a list into separate items
- Nothing New To Chase (Slack): post (message)
- Is Your Page Still There? (HTTP Request): calls an HTTP API
…plus 8 more steps. See the full node list below.
Services it uses
HTTP calls to: api.dataforseo.com
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (13)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Manual Trigger
n8n-nodes-base.manualTrigger - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - Data table
n8n-nodes-base.dataTable - If
n8n-nodes-base.if - Split Out
n8n-nodes-base.splitOut - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Google Sheets
n8n-nodes-base.googleSheets - Slack
n8n-nodes-base.slack - Error Trigger
n8n-nodes-base.errorTrigger
From the author
Quick overview This workflow runs weekly to fetch recently lost backlinks from DataForSEO, deduplicate them by referring domain, and triage each loss with a live status check. It logs results to Google Sheets, drafts recovery email angles with OpenAI for…