Claude Platform on AWS Now GA: Managed Agents, Code Execution, and Full API Parity via IAM

The Claude Platform on AWS is now generally available, providing AWS customers access to the full Claude Platform feature set through existing AWS IAM credentials, billing, and commitment retirement. This is distinct from Claude on Amazon Bedrock — here Anthropic operates the service and data is processed outside the AWS boundary, but customers get day-one access to all new API features and betas.
What's included
- Claude Managed Agents (beta) — build and deploy agents at scale
- Advisor strategy (beta) — agents consult an advisor model for intelligence boost
- Web search and web fetch — augment Claude with real-time web data
- Code execution — run Python, create visualizations, analyze data inside API calls
- Files API (beta) — upload and reference documents across conversations
- Skills (beta) — teach Claude best practices for consistent results
- MCP connector (beta) — connect to any remote MCP server without writing client code
- Prompt caching — reduce cost and latency on repeated context
- Citations — ground responses in source documents
- Batch processing — high-volume asynchronous workloads
Customers also get the Claude Console, Anthropic's development environment with a prompt improver, prompt generator, and evaluation tools. Supported models include Claude Opus 4.7, Sonnet 4.6, and Haiku 4.5, with new models shipping as they launch.
Authentication and operations
Authentication runs through AWS IAM, audit logging through CloudTrail, and billing via a single AWS invoice that retires against existing commitments. Teams use existing AWS credentials and IAM policies. The platform is available in most AWS commercial regions and supports global and U.S. inference geographies.
Choosing between Claude Platform on AWS and Amazon Bedrock
Both offer Claude models on AWS. The difference: Claude Platform on AWS is operated by Anthropic with full native API parity (including all betas), while Amazon Bedrock keeps AWS as the data processor (data stays within AWS boundary). Claude Platform on AWS is ideal for teams that want the latest features and are comfortable with data processed outside AWS.
📖 Read the full source: HN AI Agents
👀 See Also

Visual Reasoning Benchmark Results for 15 Multimodal AI Models
AIMultiple benchmarked 15 leading multimodal AI models on 200 visual reasoning questions across two tracks: chart understanding and visual logic. Gemini-3.1-pro-preview and Gemini-3-pro-preview lead the overall results, followed by GPT-5.2, Kimi-K2.5, and GPT-5.2-pro.

Trump Admin Clears Anthropic's Mythos AI Model for Government Use
The Trump administration has approved Anthropic to release its Mythos AI model to select companies and government agencies, per CNBC reports.
Debian Votes on AI/LLM Contribution Policy: What Developers Need to Know
Debian has begun voting on the future of AI/LLM contributions. The outcome will shape how AI-generated code is handled in Debian packages.

Claude vs GPT-4o: Same Double Pendulum Prompt, Different Coordinate Conventions
Claude and GPT-4o produce visually different double pendulum simulations because they interpret theta from opposite verticals — top vs bottom — while using the same renderer. The math is correct in both cases, but the mismatch reveals a subtle ambiguity in prompt interpretation.