Rudeness & toxicity
Redact profanity, hostile language, and harassment from inbound prompts
Maintaining brand safety and professional alignment requires strict content guidelines. The rudeness filter scans incoming prompts for profanity, hostile language, and harassment, and redacts matched terms before the prompt is forwarded upstream.
Remediation action: Replace with {{REDACTED}} — Offending language is identified and replaced with redaction placeholders, allowing the request to proceed to the model with the problematic content neutralized.
Example interception
Inbound hostile prompt from user:
"This is complete bullshit. Your damn software lost my order again, you idiot."What the upstream LLM actually sees:
"This is complete {{REDACTED}}. Your {{REDACTED}} software lost my order again, you {{REDACTED}}."