Generate sales leads & personalized outreach emails using Jina AI and OpenAI agents
Needs changesWhat this workflow does
This AI workflow has 20 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenAI Chat Model and Airtable. It also calls deepsearch.jina.ai over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Business_Info (Edit Fields (Set)): sets 5 fields: BUSINESS_NAME, BUSINESS_INFORMATION, BUSINESS_KEY_BENEFITS…
- Jina_API_Key (Edit Fields (Set)): sets 1 field: jina_api
- Get input records (Airtable): search
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Lead Person Research (HTTP Request): calls deepsearch.jina.ai (POST)
- Merge: merges the data from its input branches
- Merge: merges the data from its input branches
- Lead Analyzer (AI Agent): runs an AI agent, with model: OpenAI o3-mini; output parser: Structured Output Parser
- Update record (Airtable): update
- Wait: pauses before continuing
…plus 3 more steps. See the full node list below.
Services it uses
HTTP calls to: deepsearch.jina.ai
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 Lead Analyzer (v1.6), Email Content Creator (v1.7), Evaluator (v1.7): 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) Lead Analyzer (v1.6), Email Content Creator (v1.7), Evaluator (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (10)
- Manual Trigger
n8n-nodes-base.manualTrigger - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - HTTP Request
n8n-nodes-base.httpRequest - AI Agent
@n8n/n8n-nodes-langchain.agent - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Merge
n8n-nodes-base.merge - Wait
n8n-nodes-base.wait - Airtable
n8n-nodes-base.airtable - Edit Fields (Set)
n8n-nodes-base.set
From the author
This workflow uses AI agents to enrich company data from Airtable. It performs deep research to find the best decision-maker, then drafts and evaluates a personalized outreach email, and finally updates the original Airtable record with the new lead…