Anthropic detailed the isolation design behind Claude Code and Claude Cowork. The numbers turn agent security from approval prompts into sandbox, VM, and egress policy.
AWS Agent Toolkit and the AWS MCP Server GA show how coding agents can reach cloud accounts through IAM, CloudWatch, and CloudTrail.
AWS SageMaker AI now supports OpenAI-compatible inference endpoints, moving enterprise LLM friction from model deployment toward API surfaces, IAM, and routing layers.
AWS Partner Central agents turn opportunity creation into natural language, file analysis, MCP access, IAM permissions, and explicit approval for writes.
AWS AgentCore Payments previews a runtime layer where AI agents pay for APIs and MCP servers through x402, Coinbase, and Stripe wallets.
Claude Platform on AWS brings IAM, CloudTrail, and Marketplace billing to Anthropic native APIs, but its data boundary is not Bedrock.
AWS Security Agent full repository code review targets trust boundaries and data flows that traditional SAST often misses.
The AWS AI Security Framework separates answering, connected, and acting AI, making agent identity, tool authorization, and observability the new security baseline.
AWS AgentCore Browser moves browser-agent security from prompts into Chrome enterprise policies, custom root CAs, and auditable runtime controls.
AWS Agent Toolkit packages MCP servers, skills, and plugins into an official path for AI coding agents that need to work with AWS safely.
Anthropic and AWS made Claude Platform on AWS generally available, giving AWS customers a native Claude agent stack alongside Bedrock.