← Back
AWS ML Blog

Supercharge regulated workloads with Claude Code and Amazon Bedrock

•12 min read•
#anthropic#amazon#bedrock#llm#agents
Level:Advanced
For:AI Engineers
✦TL;DR

Anthropic’s Claude Opus 5.5 and Claude Sonnet 5.5 are now available on Amazon Bedrock in AWS GovCloud (US) with FedRAMP Class D and DoD IL4/IL5 certifications, enabling regulated AI‑assisted development. Bedrock offers two endpoint surfaces—**bedrock‑runtime** (AWS SDK InvokeModel/Converse APIs, Guardrails, logging) and **bedrock‑mantle** (native Anthropic Messages API, server‑side tools, Projects)—both powered by the Mantle inference engine with Zero Operator Access. Claude Code, Anthropic’s agentic coding tool, runs on these models and integrates directly with terminals, VS Code, JetBrains IDEs, and the Claude Agent SDK, allowing compliant code‑base editing and command execution. Engineers can now build AI‑driven development workflows in highly regulated environments without sacrificing security or auditability.

⚡ Key Takeaways

  • Claude Opus 5.5, Claude Sonnet 5.5, and Claude Sonnet 5 are certified FedRAMP Class D and DoD IL4/IL5 on Bedrock GovCloud.
  • Bedrock‑runtime endpoint uses AWS SDK InvokeModel and Converse APIs and supports Guardrails, Knowledge Bases, Agents, and invocation logging.
  • Bedrock‑mantle endpoint provides native Anthropic Messages API access, server‑side tools, background inference, and Projects.
  • Claude Code operates in terminals, VS Code, JetBrains, and via the Claude Agent SDK to read, edit, and execute code.
  • Runtime endpoint is available in GovCloud US‑West and US‑East; Mantle endpoint is available in GovCloud US‑West only.
💡 Why It Matters

Engineers can now embed fully audited, compliant LLM‑driven coding assistants into sensitive government or regulated workloads, accelerating development while meeting strict FedRAMP and DoD security requirements.

✅ Practical Steps

  1. Call Claude Opus 5.5 or Claude Sonnet 5.5 via the **bedrock-runtime** endpoint using the AWS SDK `InvokeModel` API to benefit from Guardrails and logging.
  2. Integrate Claude Code into your development environment (VS Code, JetBrains, or terminal) by using the Claude Agent SDK as described.

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

Introducing workload recovery and expanded infrastructure checks on Amazon SageMaker HyperPod

AWS ML Blog•#deployment

Introducing Gemini 4 Neon

Google DeepMind•#llm

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

Hugging Face Blog•#llm

Mathematical proof, powered by AI. And no hallucinations!

Amazon Science•#agents

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING