Tagged
On September 1, 2026 AWS GA’d Claude Fable 5.1 — 1M-token context, 128K output, Covered Model with 30-day retention. Fable 5 (June 9) remains the prior pin; here is the fit decision, not the press release.
The AWS European Sovereign Cloud reached GA in Brandenburg on January 15, 2026—but most EU SaaS workloads still fit standard EU regions plus DPA/SCC. This guide separates data at rest, inference routing (Bedrock geographic vs global profiles), and when sovereign cloud is worth the premium.
The official aws/agent-toolkit-for-aws repo ships 43 atomic Agent Skills across 13 category folders—plus aws-core, aws-agents, and aws-data-analytics plugins. Here is why that bundle matters for IAM and audit posture, how the tree fits together, and how to pair it with the May 6, 2026 GA AWS MCP Server.
On May 6, 2026, AWS made its managed MCP server generally available in 2 regions—with IAM guardrails, CloudWatch metrics, and CloudTrail logging—while the March 25, 2026 Agent Plugin for AWS Serverless brought packaged SAM/CDK skills into Cursor and Claude Code.
AWS just made OpenAI's frontier models, Codex, and production-ready Managed Agents available inside Amazon Bedrock — wrapped in IAM, PrivateLink, Guardrails, and CloudTrail. Here is what changes for CTOs evaluating OpenAI direct vs. AWS.
Most teams buy Bedrock Provisioned Throughput too early or too late. This is the break-even math — by token volume, by model family, and by traffic shape — that we use in real FinOps engagements to decide which Bedrock pricing mode wins.
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.
The AWS observability team built a chaos engineering game on top of the official OTel Demo. 44 injected failures. Three signals. One LLM judge. Here's everything inside it.
Build production-ready AI agents on Bedrock with tool use, multi-step workflows, and supervisor patterns. From single agents to multi-agent orchestration.
Multi-agent supervisor pattern on Bedrock: architecture, implementation, and production deployment for scalable AI workflows.
AWS Nova models vs Claude: pricing comparison, performance benchmarks, and decision framework for choosing the right Bedrock model for your enterprise AI.