Latenode

Automatically generate ChatGPT responses for Zendesk tickets

This template watches Zendesk for new tickets, sends the subject and description to ChatGPT, and posts the draft as a comment on that ticket. Agents review the comment before they send it to the customer. Connect Zendesk. ChatGPT is a Latenode AI step.

Updated Sep 16, 2026Est. run: 18sEst. cost: $0.0011
How Latenode estimates time and cost

Latenode bills workflow runtime in CPU seconds. The first 10,000 CPU seconds are free each month, then usage follows pay-as-you-go CPU-second pricing. Plug-and-Play (PnP) AI nodes are billed separately—each PnP token is $1 USD, charged pay-as-you-go at vendor cost plus a small processing fee, with no API keys required.

Full pricing — how CPU seconds work →

Workflow preview

What this template does

  • Drafts a ChatGPT reply for each new Zendesk ticket
  • Posts the draft as a ticket comment for agent review
  • Uses subject and description from the new ticket
  • Keeps Zendesk auth on the Zendesk connection

How it works

1
Trigger

Watch new Zendesk tickets

The scenario starts when Zendesk creates a ticket. Subject, description, and requester arrive with the ticket.

2
AI

Draft the reply

ChatGPT reads the subject and description and returns a reply the agent can use.

3
Action

Comment on the ticket

Zendesk adds that draft as a comment on the original ticket for the agent to review.

Setup guide

1

Connect Zendesk

Add a Zendesk connection with your domain and API token. Add a trigger for new tickets.

2

Draft with ChatGPT

Send the ticket subject and description to ChatGPT. ChatGPT is a Latenode AI step.

3

Post the comment

Add the ChatGPT text as a comment on the same Zendesk ticket. Keep it internal until an agent sends it.

Requirements

A Zendesk account Latenode can read and comment on
Permission to add comments to tickets
ChatGPT available as a Latenode AI step

FAQ

Common questions about this template

Each run uses credits on your Latenode plan. We charge for processing time (1 credit = 30 seconds). Your actual cost depends on your plan and how long the run takes. See pricing plans for plans and how credits work. Plug-and-Play AI nodes are billed separately.