AI Customer Support Assistant · WhatsApp Ready · Works for Any Business
VerifiedAI WhatsApp assistant that answers queries using live site data and chat memory.
What this workflow does
The workflow receives WhatsApp messages, processes them with an AI Agent and OpenAI model, maintains conversation history in Postgres, and retrieves fresh website content through HTTP requests before replying.
It is intended for businesses that want automated, context-aware customer support on WhatsApp without manual document uploads or model training.
Who is this for?
Small business owners, e-commerce teams, and agencies managing customer inquiries via WhatsApp who want affordable AI support without SaaS subscriptions.
What problem it solves
Manual or costly chat tools fail to provide real-time answers from live website content while maintaining conversation context across sessions.
Live workflow preview
Interactive canvas of every node and connection — scroll and click to explore. Powered by n8n's preview.
Open the template on n8n to import and run it. View source template →
What it automates
E-commerce product queries
AI fetches current product details and policies from the site to answer WhatsApp questions about stock or shipping.
Support ticket handling
Handles follow-up questions in long threads using Postgres memory to keep responses coherent without repeating info.
Agency client bots
White-label setup for multiple client domains by changing the root_url variable and WhatsApp number.
How the workflow works
The 6 nodes in this automation, in order.
- 1WhatsApp Business CloudwhatsApp
- 2Codecode
- 3AI Agent@n8n/n8n-nodes-langchain.agent
- 4OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
- 5Postgres Chat Memory@n8n/n8n-nodes-langchain.memoryPostgresChat
- 6HTTP Request Tool@n8n/n8n-nodes-langchain.toolHttpRequest
Apps & integrations used
How to set up AI Customer Support Assistant · WhatsApp Ready · Works for Any Business
- 1Import the workflow template into n8n
- 2Add credentials for OpenAI, WhatsApp Business Cloud, and Postgres
- 3Set the root_url variable to your domain
- 4Configure Meta webhook to point at the n8n webhook URL
- 5Activate the workflow and test with a WhatsApp message
How to customize this workflow
- →Replace WhatsApp trigger with Telegram or Slack node
- →Swap OpenAI Chat Model for another supported LLM
- →Extend HTTP Request Tool calls for additional site endpoints
- →Adjust AI Agent prompt for different tone or language
AI Customer Support Assistant · WhatsApp Ready · Works for Any Business: pros & cons
Pros
- +No document uploads or model fine-tuning needed
- +Live page crawling keeps answers current
- +Built-in chat memory for natural follow-ups
- +Low cost compared to dedicated SaaS tools
Cons
- –Requires WhatsApp Business Cloud API setup
- –Depends on OpenAI for all AI responses
- –Crawling limited to publicly accessible pages
Frequently asked questions
It runs an AI agent that answers WhatsApp messages using live data from any website plus conversation memory stored in Postgres.
User reviews
Verified reviews from the community shape this listing's rating.
Loading reviews…
Similar workflows
Other ai & llm automations worth a look.