Safety filter defaults
Configure default content safety filters for your agent. These filters control what content is allowed in agent responses.Channel-specific overrides can be configured in Voice configuration and Chat configuration.
| Category | Description |
|---|---|
| Violence | Controls filtering of violent content (Lenient → Strict) |
| Hate | Controls filtering of hateful or discriminatory content (Lenient → Strict) |
| Sexual content | Controls filtering of sexually explicit content (Lenient → Strict) |
| Self-harm | Controls filtering of self-harm related content (Lenient → Strict) |
Related pages
- Safety dashboard - Monitor flagged conversations
- Chat configuration - Channel-specific chat settings
- Voice configuration - Channel-specific voice settings