da Agency

Amazon Bedrock Guardrails announces general availability of cross-account safeguards

Amazon Bedrock Guardrails now enables centralized enforcement of safety controls across all AWS accounts within an organization through cross-account safeguards. Amazon Bedrock Guardrails offers configurable safeguards that help block up to 88% of harmful multimodal content from both input prompts and model responses, while filtering hallucinated responses from foundation models. Central security teams and administrators can now automatically implement these controls for all foundation model interactions in Amazon Bedrock across their organization, eliminating the operational overhead of manually configuring guardrails for each account. With cross-account safeguards, you can specify a guardrail ID from your management account in a new Amazon Bedrock policy that automatically enforces configured safeguards across all member entities including organizational units (OUs) and individual accounts for all model invocations with Amazon Bedrock. This enables operational efficiency through automatic enforcement from a single control point in your management account. You can implement organization-level enforcement for uniform baseline protection, account-level controls for specific departmental requirements, and application-specific safeguards that complement organizational policies, with the union of multiple guardrails enforced during model inference calls. Organizational safeguards in Amazon Bedrock Guardrails is now available in all AWS commercial and GovCloud regions where Bedrock Guardrails is supported. You can access this capability through the AWS management console or using the supported APIs. To learn more about implementing centralized guardrails enforcement across your organization, read the News blog, visit the Amazon Bedrock Guardrails documentation, and explore the Amazon Bedrock Guardrails service page.
Quelle: aws.amazon.com

da Agency

Amazon SageMaker Data Agent introduces charting capabilities and support for materialized views

Amazon SageMaker Data Agent now supports interactive charting, SQL analytics on Snowflake data sources, and materialized view management in Amazon SageMaker Unified Studio notebooks. Data Agent now provides a complete analytics workflow that goes beyond code generation, enabling you to explore AWS and external data sources, visualize results, and optimize query performance, all with natural language prompts.
You can ask “plot monthly revenue trends by region for 2025″ and Data Agent generates an interactive chart directly in your notebook, where you can hover over data points, and modify without writing code. When your analysis spans AWS and Snowflake, you can query Snowflake tables through external connections and join them with your AWS Glue Data Catalog data in a single prompt. Additionally, you can ask “analyze my notebook and suggest which queries would benefit from materialized views” and the agent recommends optimizations based on your query patterns, creates the views, and sets refresh schedules.
To get started, open a notebook in your SageMaker Unified Studio project and use the Data Agent chat panel. These features are available in all AWS Regions where Amazon SageMaker Unified Studio is supported. To learn more, see SageMaker Data Agent in the SageMaker Unified Studio User Guide.
Quelle: aws.amazon.com

da Agency

AWS Glue Schema Registry is now available in three more AWS regions

You can now use the AWS Glue Schema Registry, a serverless and free feature of AWS Glue, in the Asia Pacific (Jakarta), Europe (Spain), and Europe (Zurich) regions to validate and control the evolution of streaming data using registered Apache Avro, JSON, and Protobuf schema formats.
The Schema Registry acts as a centralized repository for managing data format and structure between decoupled applications in data streaming systems. By using it, you can eliminate data validation logic and cross-team coordination, improve streaming data quality, and reduce downstream application failures. Through Apache-licensed serializers and deserializers, the Schema Registry integrates with C# and Java applications developed for Apache Kafka/Amazon Managed Streaming for Apache Kafka, Amazon Kinesis Data Streams, Apache Flink/Amazon Kinesis Data Analytics for Apache Flink, and AWS Lambda. 
To get started, visit the AWS Glue Schema Registry documentation. For a full list of AWS Regions where AWS Glue Schema Registry is available, see the AWS Regional Services List.
Quelle: aws.amazon.com

da Agency

Apache Spark troubleshooting and upgrade agents now available as Kiro powers

The Apache Spark troubleshooting agent and upgrade agent for Amazon EMR are now available as Kiro powers, bringing one-click access to AI-assisted Spark operations directly in Kiro. With these powers, data engineers can reduce troubleshooting time from hours to minutes and compress Spark version upgrades from months to weeks. When a Spark job fails, the troubleshooting power identifies the root cause by analyzing logs, metrics, and configurations across EMR on EC2 and EMR Serverless, and provides specific code recommendations for PySpark applications. The upgrade power automates Spark version upgrades, such as moving from EMR 6.5 to EMR 7.12, by handling code transformation and dependency resolution through remote validation and data quality comparison on EMR. Both powers connect to Spark agents through MCP Proxy for AWS with IAM role-based authentication, and all actions are recorded in AWS CloudTrail for full auditability..
The Apache Spark troubleshooting and upgrade powers are available with Amazon EMR in all AWS commercial regions. To get started, install the Apache Spark troubleshooting power or the upgrade power from the Kiro IDE. For more information, see the troubleshooting agent and upgrade agent documentation.
Quelle: aws.amazon.com