📖 Content moderation glossary
What is sandbox mode in moderation?
In short
In moderation, sandbox mode is a test setting in which the system analyses real content and shows what it would decide, without actually hiding or removing anything.
Sandbox mode is how a team builds confidence before switching on automatic moderation. It shows which comments would be hidden, which would go to human review and why, so the rules and thresholds can be adjusted against the organisation's real audience.
Example: before automating moderation on its Facebook and Instagram pages, a retailer runs a sandbox for two weeks. It finds that complaints about delivery times would stay visible, as intended, but that a regional expression is wrongly treated as an insult, and corrects the rule.
OpenModeration offers a sandbox mode, so clients can see the decisions the system would take on their own comments before any action is applied.