Supercharge regulated workloads with Claude Code and Amazon Bedrock
aws ·
AWS has announced the availability of Anthropic's Claude Opus 5.5 and Claude Sonnet 5.5 models within Amazon Bedrock on AWS GovCloud (US) regions, enabling AI-assisted development for highly regulated workloads. These models support compliance frameworks such as FedRAMP Class D and DoD Impact Levels 4 and 5, making them suitable for environments subject to ITAR and other strict security requirements. The article details how developers can integrate these capabilities with Claude Code, an agentic coding tool that operates directly in terminals and IDEs. It provides step-by-step instructions for configuring Claude Code using either the bedrock-runtime or bedrock-mantle endpoints, highlighting differences in features like Guardrails and invocation logging. Organizations are advised to implement robust governance strategies, including IAM Identity Center integration, per-user token guardrails, and model version pinning to ensure consistent and secure deployments. The solution allows teams to accelerate everyday development tasks while maintaining data privacy and audit trails within the secure AWS GovCloud infrastructure. This release offers a compliant pathway for government agencies and aerospace customers to leverage advanced generative AI without compromising regulatory obligations.
aws