bedrock-guardrails

SKILL.md

Amazon Bedrock Guardrails provides six safeguard policies for securing and controlling generative AI applications. It works with any foundation model (Bedrock, OpenAI, Google Gemini, self-hosted) through the ApplyGuardrail API, enabling consistent safety policies across your entire AI infrastructure.

Automated Reasoning requires a separate policy document, then association with guardrail.

| NONE | No filtering | When policy doesn't apply to direction (e.g., output for PROMPTATTACK) | | LOW | Lenient filtering | Creative applications, minimal restrictions | | MEDIUM | Balanced filtering | General-purpose applications | | HIGH | Strict filtering | Enterprise, compliance-critical applications |

Comprehensive Amazon Bedrock Guardrails implementation for AI safety with 6 safeguard policies (content filters, PII redaction, topic denial, word filters, contextual grounding, automated reasoning). Use when implementing content moderation, detecting prompt attacks, preventing hallucinations, protecting sensitive data, enforcing compliance policies, or securing generative AI applications with mathematical verification. Source: adaptationio/skrillz.

View raw