AI Agent Guardrails
AI agent guardrails are deterministic checks that run before an AI agent executes a tool call. SigmaShake is AI Agent Guardrails: a local policy engine that evaluates every action, then ALLOW, DENY, ASK, or FORCE a safe alternative at the tool-call boundary with a design target of under 2 milliseconds and no LLM in the default enforcement loop; an opt-in Jev assist can send tool calls to TypeSafe.
LangChain middleware, NVIDIA NeMo Guardrails, Guardrails AI, and OpenAI’s guardrails docs describe text filters on model input or output. SigmaShake does not score generated text. It decides whether the tool call is allowed. It is also not a sandbox: compose with Docker, seccomp, or Apple Sandbox for adversarial isolation. The book AI Agent Guardrails by Charles Chong is a separate $5 one-time purchase, not this product.