Ai data extraction with dynamic prompts and Airtable

by Jimleuk ✓ · 5,467 views · created 2025-01-21 · HR, AI Summarization

What this workflow does

This AI workflow has 36 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects OpenAI Chat Model and Airtable.

How it runs

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

1. Set Airtable Vars (Edit Fields (Set)): sets 4 fields: appId, tableId, notificationUrl…
2. Get Table Schema (Airtable): get schema (base)
3. Get Table Schema (Airtable): get schema (base)
4. FieldsChanged Webhook (HTTP Request): calls an HTTP API (POST)
5. Get Prompt Fields (Code): runs custom JavaScript code
6. Get "Input" Field (Edit Fields (Set)): sets or maps fields
7. Get Webhook Payload (HTTP Request): calls an HTTP API
8. RecordsChanged Webhook (HTTP Request): calls an HTTP API (POST)
9. Parse Event (Code): runs custom JavaScript code
10. Event Type (Switch): routes items into 3 branches

…plus 18 more steps. See the full node list below.

Services it uses

OpenAI Chat ModelAirtable

Before you upgrade to n8n 3.0

Nodes used (13)

• Switchn8n-nodes-base.switch
• Coden8n-nodes-base.code
• HTTP Requestn8n-nodes-base.httpRequest
• Extract from Filen8n-nodes-base.extractFromFile
• Edit Fields (Set)n8n-nodes-base.set
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• No Operation, do nothingn8n-nodes-base.noOp
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm
• Filtern8n-nodes-base.filter
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Airtablen8n-nodes-base.airtable
• Webhookn8n-nodes-base.webhook
• Manual Triggern8n-nodes-base.manualTrigger

From the author

This n8n template introduces the Dynamic Prompts Ai workflow pattern which are incredible for certain types of data extraction tasks where attributes are unknown or need to remain flexible. The general idea behind this pattern is that the prompts for…

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