AIGuardrails
Harmful content
Block or moderate answers containing hate speech, insults, sexual content, violence or misconduct.
Harmful content
The Harmful content tab enables a filter that detects and blocks harmful content in the agent's answers.
Turn the harmful content filter on
Turn on Enable the harmful content filter so the agent blocks or moderates answers with hate speech, insults, violence or misconduct.
Enabling it makes the per-category level settings available.
Moderation level per category
Set the filter's sensitivity for each category separately:
| Category | What it detects |
|---|---|
| Hate speech | Language attacking groups on the basis of race, religion, gender and the like |
| Insults | Abuse and degrading language aimed at people |
| Sexual content | Explicit or suggestive content of a sexual nature |
| Violence | Descriptions of, or encouragement towards, violent acts |
| Misconduct | Inappropriate behaviour that does not fit the categories above |
For each, choose a moderation level:
| Level | What it does |
|---|---|
| None | No filtering — the content is not checked |
| Low | Blocks only explicitly harmful content |
| Medium | Blocks moderately harmful content |
| High | Blocks any hint of harmful content (the most restrictive) |