Lecture index
한국어English
Course Overview

Cusdis Automation Overview

Build an end-to-end comment moderation flow with n8n, Gemini, and Cusdis.

A practical beginner-friendly course for automating blog comment operations, from webhook wiring and AI moderation to conditional routing, approval APIs, and ops checklists.

Deliverable: a production-minded workflow that analyzes, delays, approves, and replies to safe comments automatically.

What you will be able to do

  • Wire Cusdis webhooks into n8n so comment events become the trigger for automation.
  • Design prompts that force Gemini into a JSON contract and post-process the output safely.
  • Combine clean-comment branching, random delay, and approval API calls into one workflow.
  • Prepare a deployment checklist and identify recovery points needed for live operations.

Chapter outline

0120m

Setup and understand the full flow

Clarify the roles of Cusdis, n8n, and Cloudflare Tunnel before touching the workflow details.

You will learn
  • Why Cusdis is a strong first automation target
  • A realistic decision rule for n8n Cloud vs self-hosted
  • How to expose a public URL for incoming webhooks
Key artifacts
  • End-to-end system flow
  • Self-hosted public URL checklist
0215m

Create the webhook trigger

Connect Cusdis comment events to the first Webhook node in n8n.

You will learn
  • Connect the webhook URL from Cusdis site settings
  • Read the input shape of the n8n Webhook node
Key artifacts
  • Sample comment webhook payload
0330m

Gemini analysis and JS normalization

Force the AI into a strict JSON contract and normalize it with defensive JavaScript.

You will learn
  • How to shape a Gemini prompt like a JSON schema
  • How to avoid a broken workflow when AI output is malformed
Key artifacts
  • Gemini moderation prompt
  • normalize-gemini-output.js
0425m

Conditional routing and approval API

Route only safe comments forward, wait for a natural delay, then send approval and reply requests.

You will learn
  • Use the If node to pass only NORMAL comments
  • Create a human-like moderation rhythm with the Wait node
  • Call the approval/reply API through the HTTP Request node
Key artifacts
  • Approval request body example
  • Operations deployment checklist
0510m

Ops review and extension ideas

Review the failure points, rollout checks, and next automation ideas needed for production.

You will learn
  • Where to debug first when the workflow fails
  • How to extend the flow into Slack alerts, archival, or moderation reports
Key artifacts
  • Operations risk memo

Hands-on evidence

Full workflow structure

See the moderation flow from comment event to final approval request.

Full workflow structure

Gemini node setup

A concrete example of configuring AI as a structured moderation step, not a vague chat call.

Gemini node setup

Approval API request

Inspect the request shape used in the final production-facing step.

Approval API request

JSON contract example

This is the minimum response contract the AI is asked to produce.

{
  "classification": "NORMAL | SPAM | REVIEW",
  "reason": "short explanation",
  "replyDraft": "human-sounding reply draft"
}

Practice assets

Document

Example README

Start here for the practice flow and a quick map of the example files.

JSON

Webhook payload sample

Inspect the incoming comment event shape sent by Cusdis.

Prompt

Gemini prompt contract

A prompt template that forces structured JSON output.

Source

JS normalization code

A defensive parsing example that absorbs malformed AI responses.

API example

Approval request body

An example request body for comment approval and reply posting.

Checklist

Ops checklist

A deployment-time checklist for stable operations.

FAQ

Can I follow this without being strong in code yet?

Yes. The main goal is to see webhooks, JSON, and branching in a real flow. The JavaScript examples stay short and purpose-driven.

Can I practice without n8n Cloud?

Yes. A self-hosted n8n instance plus Cloudflare Tunnel is enough to reproduce the full workflow, and the course covers that path.

Is auto-approval too risky?

That is exactly why the course includes JSON contracts, branching rules, random delay, and an ops checklist. The goal is a safer moderation loop, not blind auto-approval.