A defense-in-depth playbook for the AI systems you actually ship: input and output filtering, system-prompt hardening and instruction hierarchy, sandboxing and least-privilege for tool-using agents, human-in-the-loop gates, structured-output and allow-list constraints, PII redaction, injection detection with heuristics and classifier models, rate limiting and spend caps, and red-teaming your own app. The tooling — NeMo Guardrails, Llama Guard, Guardrails AI, LLM Guard, Presidio — and the honest trade-offs of each layer.
Guardrails
-
Guardrails for Production LLM Applications