Create purchase orders from Gmail using Groq LLM, Airtable, and Google Sheets
Ready for 3.0What this workflow does
This AI workflow has 15 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Gmail, Groq Chat Model, Airtable and Google Sheets.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Code: runs custom JavaScript code
- Gmail: get many
- Set: Format Gmail Data (Edit Fields (Set)): sets 2 fields: raw_text, requester
- LLM: Parse Request (Basic LLM Chain): sends a prompt to an LLM, with model: Model: Groq LLM; output parser: Parse: Structured JSON
- Set: Extract AI Output (Edit Fields (Set)): sets 2 fields: is_urgent, items
- Airtable: search
- Code: runs custom JavaScript code
- Router: Evaluate Status (Switch): routes items into 3 branches
- Airtable: create or update
- Sheets: Log Approval (Google Sheets): append or update
…plus 2 more steps. See the full node list below.
Services it uses
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 (10)
- Manual Trigger
n8n-nodes-base.manualTrigger - Code
n8n-nodes-base.code - Gmail
n8n-nodes-base.gmail - Edit Fields (Set)
n8n-nodes-base.set - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Airtable
n8n-nodes-base.airtable - Switch
n8n-nodes-base.switch - Google Sheets
n8n-nodes-base.googleSheets
From the author
Quick overview This workflow pulls unread “purchase request” emails from Gmail, uses a Groq-hosted LLM to extract line items and urgency into structured JSON, matches items against an Airtable catalog to apply pricing and vendors, then logs approvals to…