Auto-generate WhatsApp proposals from voice or text using GPT & APITemplate
Needs changesWhat this workflow does
This AI workflow has 15 nodes and runs on WhatsApp events (messages). Along the way it connects OpenAI Chat Model, WhatsApp Business Cloud, OpenAI and Airtable and 1 more.
How it runs
Trigger: On WhatsApp events (messages).
- Split Out: splits a list into separate items
- Switch: routes items into 2 branches
- WhatsApp Business Cloud: media url get
- Edit Fields (Edit Fields (Set)): sets 1 field: text
- HTTP Request: calls an HTTP API
- Edit Fields (Edit Fields (Set)): sets 1 field: message_type
- OpenAI: transcribe (audio)
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 2 tools (Get Info, Calculator); memory: Simple Memory
- APITemplate.io: work with pdf
- WhatsApp Business Cloud: send
Services it uses
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 AI Agent (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI 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 (13)
- OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - Switch
n8n-nodes-base.switch - HTTP Request
n8n-nodes-base.httpRequest - OpenAI
@n8n/n8n-nodes-langchain.openAi - Edit Fields (Set)
n8n-nodes-base.set - Split Out
n8n-nodes-base.splitOut - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - WhatsApp Business Cloud
n8n-nodes-base.whatsApp - Calculator
@n8n/n8n-nodes-langchain.toolCalculator - Airtable Tool
n8n-nodes-base.airtableTool - AI Agent
@n8n/n8n-nodes-langchain.agent - APITemplate.io
n8n-nodes-base.apiTemplateIo
From the author
How it works • Transcribes a WhatsApp voice or text message from a prospect using Whisper or GPT • Extracts key information (name, need, context, urgency) via AI • Matches the most relevant service pack by comparing the prospect’s need with Airtable data •…