All features
Moderate
Content moderation
AI-assisted toxicity + brand-safety scoring. Audit log of every approve / reject + reason.
Pro + Enterprise. Standalone Brand-Safety API on the API platform.
Content moderation
Moderating
Brand-safety score · six axes · pre-publish
Score
94 / 100
Axes
6
p95 inference
48 ms
Moderation · livelive
What you get
- Toxicity, hate, NSFW, IP-infringement detection
- Per-brand safety profiles you tune from the dashboard
- Auto-block hard rules; queue soft rules for a human
- Audit log every decision with a reason and a reviewer
How it works
- Step 01
Score every asset
Six-dimension score returned per asset before it enters the public surface.
- Step 02
Apply the policy
Per-brand profile blocks, warns or queues based on the score.
- Step 03
Audit forever
Every decision, every reviewer, every reason, exportable for legal review.
What’s included
- Six-dimension brand-safety scoring
- Per-brand custom profiles
- Hard-block + queue + soft-warn policies
- Reviewer dashboard with hot-key approvals
- Audit log + reason capture
Try it on your store
See content moderation live in 30 seconds.
Drop your email, we’ll spin up a sample workspace with this feature pre-loaded and send a 5-minute walkthrough video.
