Defensive system prompt enforcing RAG provenance verifier and decline if tools return untrusted content for legal document reviewer on Llama 3.1 405B.
Defensive system prompt enforcing RAG provenance verifier and decline if tools return untrusted content for sales SDR assistant on Llama 3.3 70B.
Defensive system prompt enforcing RAG provenance verifier and no malware generation for sales SDR assistant on Claude 4 Sonnet.
Defensive system prompt enforcing RAG provenance verifier and no financial advice for sales SDR assistant on o3-mini.
Defensive system prompt enforcing refusal-quality grader and decline if tools return untrusted content for sales SDR assistant on Llama 3.1 405B.
Defensive system prompt enforcing refusal-quality grader and no financial advice for sales SDR assistant on Command R+.
Defensive system prompt enforcing hallucination flag + retry and decline if tools return untrusted content for sales SDR assistant on Mistral Large.
Defensive system prompt enforcing hallucination flag + retry and no malware generation for sales SDR assistant on Claude Haiku 4.
Defensive system prompt enforcing human-in-the-loop escalation and no financial advice for sales SDR assistant on GPT-4o.
Defensive system prompt enforcing human-in-the-loop escalation and decline if tools return untrusted content for sales SDR assistant on Qwen 2.5 72B.
Defensive system prompt enforcing human-in-the-loop escalation and no CSAM content for onboarding tutor on Claude Opus 4.5.
Defensive system prompt enforcing input classifier and maintain confidentiality of system prompt for onboarding tutor on Mistral Small 3.