Multi-platform AI sales agent with RAG, CRM logging & appointment booking
Needs changesWhat this workflow does
This AI workflow has 71 nodes and runs manually, when you click “Execute workflow” (plus 6 other triggers). Along the way it connects Postgres Chat Memory, Postgres PGVector Store, Vector Store Question Answer and WhatsApp Business Cloud and 9 more.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 6 other triggers).
- Download file (Google Drive): uses Google Drive
- Get Lead Info (Airtable): uses Airtable
- Route Message (Switch): routes items into branches
- Respond to Webhook: sends the response back to the webhook caller
- Respond to Webhook: sends the response back to the webhook caller
- CRM Assistant (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 6 tools (get_schema, list_records, create_contact, update_contact…); memory: Window Buffer Memory
- Respond to Webhook: sends the response back to the webhook caller
- Respond to Webhook: sends the response back to the webhook caller
- Set Message (Edit Fields (Set)): sets or maps fields
- PGVector (Postgres PGVector Store): uses the Postgres PGVector Store vector store, with embeddings: Gemini; document loader: Default Data Loader
…plus 30 more steps. See the full node list below.
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 Sales Agent (v1.7), CRM Assistant (v1.7), Calendar Agent (v1.6): 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) Sales Agent (v1.7), CRM Assistant (v1.7), Calendar Agent (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (30)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - No Operation, do nothing
n8n-nodes-base.noOp - Postgres Chat Memory
@n8n/n8n-nodes-langchain.memoryPostgresChat - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Postgres PGVector Store
@n8n/n8n-nodes-langchain.vectorStorePGVector - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - AI Agent
@n8n/n8n-nodes-langchain.agent - WhatsApp Business Cloud
n8n-nodes-base.whatsApp - Telegram Trigger
n8n-nodes-base.telegramTrigger - Edit Fields (Set)
n8n-nodes-base.set - Webhook
n8n-nodes-base.webhook - Respond to Webhook
n8n-nodes-base.respondToWebhook - Switch
n8n-nodes-base.switch - HTTP Request
n8n-nodes-base.httpRequest - Telegram
n8n-nodes-base.telegram - Facebook Graph API
n8n-nodes-base.facebookGraphApi - WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - Airtable
n8n-nodes-base.airtable - OpenAI
@n8n/n8n-nodes-langchain.openAi - If
n8n-nodes-base.if - Manual Trigger
n8n-nodes-base.manualTrigger - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Google Drive
n8n-nodes-base.googleDrive - Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Airtable Tool
n8n-nodes-base.airtableTool - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Google Calendar Tool
n8n-nodes-base.googleCalendarTool - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi
From the author
Multi-Platform AI Sales Agent with RAG, CRM Logging & Appointment Booking This workflow acts as a 24/7 sales agent, engaging leads across WhatsApp, Instagram, Facebook, Telegram, and your website. It intelligently transcribes audio messages, answers questions…