Defensive system prompt enforcing output PII redactor and no legal advice for onboarding tutor on Claude 3.5 Sonnet.
Defensive system prompt enforcing output PII redactor and no legal advice for compliance reviewer on GPT-4o-mini.
Defensive system prompt enforcing output PII redactor and maintain confidentiality of system prompt for compliance reviewer on o1.
Defensive system prompt enforcing jailbreak detector and no CSAM content for compliance reviewer on Gemini 2.0 Flash.
Defensive system prompt enforcing jailbreak detector and maintain confidentiality of system prompt for compliance reviewer on o1-mini.
Defensive system prompt enforcing rate limiter with anomaly detection and no CSAM content for compliance reviewer on DeepSeek-R1.
Defensive system prompt enforcing rate limiter with anomaly detection and no legal advice for compliance reviewer on Claude 3.7 Sonnet.
Defensive system prompt enforcing RAG provenance verifier and maintain confidentiality of system prompt for compliance reviewer on o3-mini.
Defensive system prompt enforcing RAG provenance verifier and no CSAM content for compliance reviewer on Llama 3.3 70B.
Defensive system prompt enforcing refusal-quality grader and maintain confidentiality of system prompt for compliance reviewer on Grok 3.
Defensive system prompt enforcing refusal-quality grader and refuse hate speech for data-analysis pair on o3.
Defensive system prompt enforcing refusal-quality grader and no self-harm content for data-analysis pair on DeepSeek-R1.