ai-security

On Jul 27, 2026, AWS launched the Security Hub MCP App preview—8 read-only tools that bring exposure findings, attack paths, and remediation guidance into Claude Desktop at no additional cost for Security Hub customers.

Bedrock Automated Reasoning checks ground LLM outputs against formal logic policies you encode and mathematically validate that the response is consistent with the policy. This guide covers when to use Automated Reasoning vs contextual grounding, how to author the policy in production, the integration with Bedrock Guardrails, and the regulated use cases (HR, insurance, eligibility, regulatory determinations) where the difference matters.

EU AI Act compliance on AWS — risk classification, prohibited practices, GPAI obligations, the high-risk Annex III framework (enforceable 2 August 2026), and the AWS-native control mapping using Bedrock Guardrails, SageMaker Model Cards, and Audit Manager governance.