Cacuda Automod

Automated content moderation,
privacy first.

Build moderation pipelines that scan, decide, and act — without ever storing your data. Connect your platform in minutes, not days.

How Automod works

Four steps from setup to fully automated moderation.

1

Connect your platform

Install a plugin for WordPress or Drupal, or set up a webhook for any platform that can send HTTP requests.

2

Build your pipeline

Drag and drop triggers, detectors, and actions onto a visual canvas. Connect them into a moderation flow.

3

Configure actions

Set thresholds, choose what happens on pass or fail — approve, reject, flag, or notify. Add conditional branches for complex logic.

4

Content flows automatically

Activate your pipeline and content is moderated in real-time. Zero retention — data is processed and immediately discarded.

Privacy-first moderation

Your content is never stored, logged, or used for training. Automod processes data in memory and discards it immediately.

Real-time processing

Content is analysed in memory and immediately discarded after the verdict

No logs, no storage

We don't retain your content on disk, in databases, or in any cache

Never used for training

Your data is never fed back into our models or shared with any third party

GDPR compliant by design

Zero-retention architecture means there's nothing to delete or request

HMAC-signed webhooks

Every payload is cryptographically signed to verify integrity and authenticity

Encrypted in transit

All communication uses TLS encryption between your platform and Cacuda

What your pipeline can check

Six ML-powered detection models plus rule-based checks — combine them however you need.

AI Image Detection

5 credits

Detect AI-generated images from DALL-E, Midjourney, Stable Diffusion, and more.

NSFW Image Detection

3 credits

Flag explicit, violent, or unsafe imagery in real time.

Age Verification

3 credits

Estimate whether a face belongs to a minor or adult for compliance workflows.

AI Text Detection

2 credits

Identify AI-written content from ChatGPT, Claude, Gemini, and other LLMs.

Spam Detection

1 credit

Catch spam, phishing, and low-quality content before it reaches your users.

NSFW Text Detection

1 credit

Detect explicit language, hate speech, harassment, and toxic content.

Free

Rule-based checks

Word list matching, regex patterns, and content length checks cost zero credits. Use them as pre-filters to save on ML detection costs.

Simple credit-based pricing

Automod pipelines are free to create. You only pay for the detection models each pipeline calls.

Detection ModelCredits per Call
AI Image Detection5
NSFW Image Detection3
Age Verification3
AI Text Detection2
Spam Detection1
NSFW Text Detection1
Word List / Regex / Length0 (free)

Example: A WordPress comment moderation pipeline with Spam + NSFW Text detection costs 2 credits per comment. On the Pro plan (1,000 credits/month), that covers 500 comments.

Ready to automate?

Build your first moderation pipeline in under 5 minutes. No credit card required.