Run multi-step cold email sequences with OpenAI, LinkedIn, Qdrant and NocoDB
Needs changesWhat this workflow does
This AI workflow has 101 nodes and runs on a schedule (every week at 16:00) (plus 4 other triggers). Along the way it connects OpenAI Chat Model, Embeddings OpenAI and Qdrant Vector Store. It also calls professional-network-data.p.rapidapi.com, api.openai.com and api.anthropic.com over HTTP.
How it runs
Trigger: On a schedule (every week at 16:00) (plus 4 other triggers).
- Get 1st Email Sending List (HTTP Request): calls an HTTP API
- Get Leads Data (HTTP Request): calls an HTTP API
- Get Leads Data (HTTP Request): calls an HTTP API
- Get Leads Data (HTTP Request): calls an HTTP API
- Insert Data to Qdrant (Qdrant Vector Store): stores documents in the Qdrant vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
- Split Out: splits a list into separate items
- Update Email Sequence (Code): runs custom JavaScript code
- Update Email Sequence (Code): runs custom JavaScript code
- Update Email Sequence (Code): runs custom JavaScript code
- Batch Process Emails (Loop Over Items (Split in Batches)): loops over the items in batches
…plus 71 more steps. See the full node list below.
Services it uses
HTTP calls to: professional-network-data.p.rapidapi.com, api.openai.com, api.anthropic.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Email Availability Checker Agent (v1.8), User Summary Generator Agent (v1.8), Email Drafting Agent 9 (v1.8)…: replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Email Availability Checker Agent (v1.8), User Summary Generator Agent (v1.8), Email Drafting Agent 9 (v1.8), Email Drafting Agent 10 (v1.8), Cold Email Generator Agent (v1.8), Email Content Enhancement Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (18)
- OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - AI Agent
@n8n/n8n-nodes-langchain.agent - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Code
n8n-nodes-base.code - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - HTTP Request
n8n-nodes-base.httpRequest - Think Tool
@n8n/n8n-nodes-langchain.toolThink - Execute Sub-workflow
n8n-nodes-base.executeWorkflow - If
n8n-nodes-base.if - Split Out
n8n-nodes-base.splitOut - Aggregate
n8n-nodes-base.aggregate - n8n Form Trigger
n8n-nodes-base.formTrigger - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Wait
n8n-nodes-base.wait - Merge
n8n-nodes-base.merge
From the author
Quick overview This primary orchestrator workflow automates multi-step cold email campaigns. It enriches lead profiles using LinkedIn data via RapidAPI, generates hyper-personalized email copy using OpenAI and a Qdrant knowledge base, and tracks follow-up…