Automate AI-Powered WhatsApp Sales with DeepSeek AI, Google Sheets, and Gmail Notifications

This n8n workflow streamlines your sales process by leveraging AI to respond to WhatsApp messages, managing customer data in Google Sheets, and sending internal Gmail notifications. It acts as an intelligent assistant, ensuring timely and relevant communication with potential customers.

What it does

This workflow is designed to:

1. Receive WhatsApp Messages: It listens for incoming WhatsApp messages via a webhook, acting as the entry point for new customer inquiries.
2. Process with AI Agent: It utilizes an AI Agent (powered by DeepSeek Chat Model) to understand the message content and generate appropriate responses.
3. Maintain Chat History: It leverages a Postgres Chat Memory to keep track of conversation history, allowing the AI to provide context-aware responses.
4. Route AI Responses: It uses an "If" node to potentially route AI-generated responses based on certain conditions (though the specific conditions are not defined in the provided JSON, it indicates a branching logic capability).
5. Perform No Operation: A "No Operation" node is present, which typically serves as a placeholder or a path for actions that are intentionally left blank or for future expansion.
6. (Implicit - based on directory name): While not explicitly visible in the provided JSON, the directory name suggests further integration with Google Sheets for data management and Gmail for notifications. These steps would likely follow the AI processing and conditional routing.

Prerequisites/Requirements

To use this workflow, you will need:

• n8n Instance: A running n8n instance to import and execute the workflow.
• WhatsApp Webhook: A mechanism to send incoming WhatsApp messages to the n8n webhook URL. This often involves a third-party WhatsApp API provider (e.g., Twilio, MessageBird, etc.) that can forward messages to a custom webhook.
• DeepSeek API Key: An API key for the DeepSeek Chat Model to enable the AI Agent functionality.
• PostgreSQL Database: Access to a PostgreSQL database for the Postgres Chat Memory node to store and retrieve chat history. You will need the connection details (host, port, database name, user, password).
• Google Sheets Account (Implicit): If integrating with Google Sheets for customer data.
• Gmail Account (Implicit): If sending Gmail notifications.

Setup/Usage

1. Import the Workflow: Download the provided JSON and import it into your n8n instance.
2. Configure Webhook:
   • Activate the Webhook node.
   • Copy the generated webhook URL.
   • Configure your WhatsApp API provider to send incoming messages to this URL.
3. Configure DeepSeek Chat Model:
   • Open the DeepSeek Chat Model node.
   • Provide your DeepSeek API key in the credentials section.
4. Configure Postgres Chat Memory:
   • Open the Postgres Chat Memory node.
   • Set up your PostgreSQL database credentials (host, port, database, user, password) to allow the node to connect and store chat history.
5. Configure AI Agent:
   • Review the AI Agent node settings. Ensure it's correctly configured to use the DeepSeek Chat Model and Postgres Chat Memory.
6. Review "If" Node:
   • Examine the If node. Currently, its conditions are not defined in the JSON. You will need to set up the conditions based on how you want to route messages (e.g., if the AI detects a specific intent, if a keyword is present, etc.).
7. Add Google Sheets and Gmail Nodes (Optional):
   • If you intend to use Google Sheets for data management and Gmail for notifications, add the respective n8n nodes after the If node (or within its branches).
   • Configure their credentials and operations (e.g., "Google Sheets: Add Row" for new leads, "Gmail: Send Email" for internal alerts).
8. Activate the Workflow: Once all configurations are complete, activate the workflow in n8n.

This workflow provides a robust foundation for automating WhatsApp sales interactions with intelligent AI responses and historical context.