Kategorie: Amazon AWS

AWS Transform now supports model-to-model migration assessment for generative AI workloads

AWS Transform now offers a model-to-model migration custom transformation that assesses your generative AI workloads and produces a comprehensive migration plan for moving from third-party providers to Amazon Bedrock. The AI-powered agent scans your codebase, identifies every AI SDK and model in use, gathers your migration requirements through interactive questions, and maps models to Bedrock equivalents with transparent cost comparisons and production-ready code changes. This managed custom transformation helps organizations consolidate their AI workloads on AWS to gain IAM-based security, VPC endpoint isolation, prompt caching, Amazon Bedrock Guardrails, and unified operational tooling through Amazon CloudWatch.   The transformation supports migrations from OpenAI, Google Gemini, direct Anthropic SDK usage, and open-source models via LiteLLM or Ollama. It handles direct SDK integrations, framework-wrapped patterns such as LangChain and LlamaIndex, agentic architectures including CrewAI and LangGraph, and multi-provider routing layers — preserving your application architecture while swapping only the model layer. The agent includes intelligent cost optimization with tiered model routing recommendations, prompt caching analysis, and model lifecycle awareness that excludes models within 90 days of end-of-life from all recommendations. For some workloads, it recommends Amazon Bedrock’s OpenAI-compatible endpoints as a zero-code-change migration path.
AWS Transform model-to-model migration is available in all AWS Regions where AWS Transform is offered, at no additional charge beyond standard AWS Transform pricing. To get started, install the ATX CLI and run the mke-genai-model-migration custom transformation against your codebase. To learn more, see the AWS Transform Custom Transformations documentation and the announcement blog.
Quelle: aws.amazon.com

Amazon Bedrock Guardrails announces a new API targeting agentic AI workflows

Amazon Bedrock Guardrails now offers the InvokeGuardrailChecks API, a new resourceless API that lets you apply individual safeguards at any point in your agentic AI applications without creating guardrail resources. The API provides granular, per-request control over which safeguards to run at each step of your agent loop, returning numeric severity and confidence scores so you can implement custom thresholds and actions, whether to block, pass, retry, or log based on your specific requirements.
Agentic AI applications operate through iterative loops; planning tasks, calling tools, processing outputs, and iterating again while often executing dozens of steps for a single request. Each step carries a different risk profile, making a one-size-fits-all guardrail difficult to scale. The InvokeGuardrailChecks API addresses this by operating in detect-only mode with no guardrail IDs to track and no versions to manage. You specify which safeguards to run directly in each request, making it straightforward to add, remove, or adjust checks as your workflows evolve.
The API supports content filters (detecting harmful content across categories including hate, violence, sexual, insults, and misconduct), prompt attack detection (identifying jailbreak, prompt injection, and prompt leakage as independent standalone checks), and sensitive information filters (detecting supported PII entity types). Prompt attack detection is exposed as a separate safeguard, giving you the granularity to invoke each supported attack vector independently.
The InvokeGuardrailChecks API is available today in the following AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (London), Europe (Stockholm), Asia Pacific (Tokyo), and Asia Pacific (Sydney).
To learn more, visit the Amazon Bedrock Guardrails technical documentation.
Quelle: aws.amazon.com

Amazon CloudWatch introduces native OpenTelemetry metrics with PromQL querying and per-GB pricing

Amazon CloudWatch now natively supports OpenTelemetry metrics. You can send metrics via the OpenTelemetry Protocol (OTLP) and query them using Prometheus Query Language (PromQL), with per-GB ingestion pricing and 15 months of storage included.
This allows you to consolidate custom application metrics and AWS vended metrics from more than 70 services in a single solution, queryable together in PromQL. CloudWatch exposes a Prometheus-compatible query API, so teams already using OpenTelemetry, Prometheus, or Grafana can use CloudWatch as a destination that fits seamlessly with their existing tools.
Available in all commercial AWS Regions except Middle East (UAE), Middle East (Bahrain), and Israel (Tel Aviv). For pricing details, see the Amazon CloudWatch pricing page. To get started, see the Amazon CloudWatch metrics documentation.
Quelle: aws.amazon.com

AWS Partner Central agents now accelerate co-selling on every deal

Starting today, AWS Partner Central agents qualify every co-sell opportunity in real time and make recommendations that drive AWS engagement and accelerate deal progression. Building on the AWS Partner Central agents released on March 16, 2026, the agent can act on the partner’s behalf through conversation to enrich the opportunity details. This eliminates waiting for manual review, so partners build a stronger pipeline and progress deals faster. Now, each opportunity is matched to a co-sell motion that determines AWS engagement: AWS field-engaged, where an AWS sales team collaborates directly; Agent-engaged, where the agent strengthens the submission to increase AWS engagement; and Partner-led, where the partner drives the deal with agent support. Across all motions, the agent provides customer insights, recommendations, and sales plays, and each opportunity receives an Opportunity Quality Score that measures co-sell readiness and directly influences how AWS engages. The agent recommends how to improve this score, and as the opportunity improves, the score and motion recalculate in real time, moving it closer to AWS engagement. The new enhanced experience is available today to AWS Partners in all commercial AWS Regions. To get started, log in to AWS Partner Central and access opportunity management. Partners can also use the agentic experience in native AI tools like Amazon Quick and Kiro, or through MCP in their own CRM. See the Partner Central agents MCP server guide to get started.
Quelle: aws.amazon.com

AWS announces AWS Blocks, an open-source framework for composing application backends on AWS (Preview)

Today, AWS announces the public preview of AWS Blocks, an open-source TypeScript framework for application developers who want backend capabilities on AWS removing the need to learn infrastructure tools. AWS Blocks runs a fully functional local environment with Postgres, authentication, and real-time messaging, no AWS account required. When ready to deploy, the same application code runs on production AWS services with zero changes, and developers can drop into AWS CDK at any point for direct resource configuration.
A developer building a SaaS application can add database tables, user authentication, AI agents, file uploads, and background jobs in a single session, test the full stack locally, and deploy to AWS when ready. Built-in guidance for AI coding tools enables correct architecture without custom configuration, and end-to-end type safety flows from the data schema to the frontend without a code generation step. At preview, supported frontend frameworks include SPAs (e.g. Vite + React) and SSR frameworks such as Next.js, Nuxt, and Astro. AWS Blocks is available at no additional charge. You pay only for the AWS services your application uses.
AWS Blocks deploys to all commercial AWS regions.
To get started, run npx @aws-blocks/create-blocks-app. Read more here:

AWS Blocks product page
Getting started guide in the AWS Blocks Developer Guide
AWS Blocks on GitHub

Quelle: aws.amazon.com

Amazon Redshift RG instances powered by AWS Graviton now available in additional regions

Amazon Redshift is expanding the general availability of RG instances — powered by AWS Graviton processors — to three additional AWS Regions: Africa (Cape Town), Asia Pacific (Bangkok), and Mexico (Central). Amazon Redshift’s new Graviton-based RG instances deliver up to 4.2X better price-performance for data warehouse workloads compared to other data warehouses, run workloads up to 2.4x faster than previous-generation RA3 instances, and cost 30% less per vCPU. Customers in Cape Town (af-south-1), Bangkok (ap-southeast-7), and Mexico Central (mx-central-1) can provision rg.xlarge and rg.4xlarge node types — ideal for a wide range of workloads from smaller development environments to production data warehouse deployments. Customers can upgrade their existing RA3 provisioned instances to RG instances and immediately benefit from improved query performance and reduced compute costs. RG instances come with additional cost savings built in by default. With Amazon Redshift incremental manual snapshots, customers now pay less for backup storage as snapshot costs are metered based on unique data blocks rather than total snapshot size. Additionally, RG instances eliminate Redshift Spectrum scanning charges, meaning customers no longer pay for data scanned in Amazon S3 via Spectrum — further reducing the total cost of running data lake queries. To get started, visit the Amazon Redshift documentation and the RG instances pricing page.
Quelle: aws.amazon.com

AWS Sign-in now supports resource-based policies and resource control policies

AWS Sign-in now supports resource-based policies and resource control policies (RCPs) for the AWS Management Console. You can use these policies to restrict console sign-in to expected networks. Policies are evaluated during sign-in and whenever the console session requests new credentials.
Resource-based policies apply to individual AWS accounts. Resource control policies apply organization-wide through AWS Organizations. You can combine these policies with AWS Management Console Private Access to control both which networks users can sign in from and which accounts they can access.
AWS Sign-in resource-based policies and RCPs are available at no additional cost in all AWS commercial Regions. To learn more, see the AWS Sign-in User Guide. For API details, see the AWS Sign-in API Reference.
Quelle: aws.amazon.com

Amazon CloudWatch introduces Log Analytics for unified log analysis

Amazon CloudWatch now offers Log Analytics, a unified console experience that brings together CloudWatch Logs Insights for querying and analyzing log data, Live Tail for real-time log streaming, and Contributor Insights for identifying top contributors – all in one place. With this launch, customers can execute multiple queries in different tabs and use all existing Logs Insights features such as patterns, saved queries with parameters, facets for interactive log exploration, natural language query generation, and visualizations. Live Tail and Contributor Insights are also accessible from within Log Analytics, which is the default experience. Customers who opt out will see Logs Insights, Live Tail, and Contributor Insights alongside Log Analytics. Log Analytics is available in all commercial AWS Regions. Log Analytics uses the same pricing as its underlying capabilities – Logs Insights queries, Live Tail, and Contributor Insights. For pricing details, see CloudWatch pricing. To get started, select Log Analytics in the CloudWatch console. Learn more in the CloudWatch Logs documentation.
Quelle: aws.amazon.com

Amazon FSx for OpenZFS now supports on-demand data replication across AWS opt-in Regions

Amazon FSx for OpenZFS now supports on-demand data replication across AWS opt-in Regions, enabling you to easily and efficiently transfer incremental point-in-time snapshots of your volumes beyond AWS Regions that are enabled by default. On-demand data replication provides a simple and resilient way to implement disaster recovery, replicate production data to a different Region or account, and enable lower latency data access for your global customer base or workforce.
Amazon FSx for OpenZFS provides fully managed, cost-effective, shared file storage powered by the popular OpenZFS file system, with rich data management capabilities like snapshots, data cloning, and compression, along with sub-millisecond latencies and up to 10 GB/s of throughput. Opt-in Regions are AWS Regions that are disabled by default, in contrast to regions that are enabled by default. Previously, on-demand data replication was supported only between accounts in AWS Regions that are enabled by default. Starting today, you can replicate snapshots to and from opt-in Regions, expanding the AWS Regions where you can build cross-Region disaster recovery and data distribution architectures.
On-demand data replication across opt-in Regions is available in all AWS Regions where Amazon FSx for OpenZFS is offered, including the supported opt-in Regions. There is no additional charge for on-demand data replication. Standard AWS data transfer charges apply when replicating across AWS Regions or accounts. To get started, visit the Amazon FSx console or refer to the on-demand replication documentation. To learn more, visit the Amazon FSx for OpenZFS product page.
Quelle: aws.amazon.com

Amazon Bedrock AgentCore Memory now supports strictly consistent metadata for long-term memory

Amazon Bedrock AgentCore Memory extracts useful information from short-term memory and stores it as long-term memory records. Metadata on these records helps organize, filter, and route them for retrieval. Previously, metadata values could only be inferred by the LLM during extraction. Now, you can also attach metadata values directly from your application, ensuring they pass through extraction and consolidation exactly as supplied with no LLM inference. When you set a metadata key’s extraction type to STRICTLY_CONSISTENT, the value you provide on the short-term memory event is the value that lands on the resulting long-term memory record unchanged.
Strictly consistent metadata also isolates how events are grouped. Events sharing the same values are extracted together and consolidated together. Records with different values are never merged, even if semantically similar. This enables department-scoped retrieval, compliance boundaries between regulated and standard records, and multi-tenant memory where each tenant’s data is processed independently.
You can configure up to three strictly consistent keys per strategy. The feature is supported on semantic, user preference, and episodic strategies, including custom overrides. Keys must be of type STRING and declared in the memory’s indexed keys. Both LLM-inferred and strictly consistent keys can coexist on the same memory resource. To get started, see Long-term memory metadata. Amazon Bedrock AgentCore Memory strictly consistent metadata is available in all AWS Regions where AgentCore Memory is supported.
Quelle: aws.amazon.com