n8n Customer Support Messaging AI
Contributed by Sabrina Ramonov 🍄. From the community directory at agents.sabrina.dev, republished with permission and full credit.
This n8n workflow demonstrates a simple approach to improve chat UX by staggering an AI Agent's reply for users who send in a sequence of partial messages and in short bursts.
How it works
Twilio webhook receives user's messages which are recorded in a message stack powered by Redis.
The execution is immediately paused for 5 seconds and then another check is done against the message stack for the latest message. The purpose of this check lets us know if the user is sending more messages or if they are waiting for a reply.
The execution is aborted if the latest message on the stack differs from the incoming message and continues if they are the same. For the latter, the agent receives the buffered messages up to that point and is able to respond to them in a single reply.
Requirements
- A Twilio account and SMS-enabled phone number to receive messages.
- Redis instance for the messages stack.
- OpenAI account for the language model.
Customising the workflow
This workflow should work for other common messaging platforms such as WhatsApp and Telegram.
Is 5 seconds too long or too short? Adjust the wait threshold to suit your customers.
Tools used: Twilio, Redis, OpenAI
Download the workflow template (JSON)
Want this running in your business? KOBA42 builds and operates automations like this one.