All news with #amazon bedrock tag

🧠 Amazon Bedrock AgentCore Memory now supports metadata on long-term memory (LTM) records, enabling agents to tag, filter, and retrieve memories using structured attributes alongside semantic search. You can define up to ten indexed keys per memory resource with STRING, NUMBER, and STRING_LIST types and apply operator filters to refine retrieval results. Metadata can be attached at ingestion or inferred automatically by the LLM using extraction instructions defined on the memory resource. This capability is available today in all AWS Regions where AgentCore Memory is supported.

🔒 Amazon announces that Bedrock AgentCore is now available in the AWS GovCloud (US-West) Region, bringing enterprise-grade agentic AI to workloads with elevated compliance and data residency requirements. AgentCore is a managed platform for building, deploying, and operating AI agents at scale without customers managing infrastructure. Core capabilities include AgentCore Runtime for session-isolated, long-running agents; AgentCore Gateway, which uses the Model Context Protocol to convert APIs and Lambda functions into agent-ready tools with controlled access to enterprise services; AgentCore Identity for integrated authentication and permission delegation; and AgentCore Observability and Evaluations for real-time monitoring and continuous quality assessment in production.

🔒 Amazon announced AgentCore availability in the AWS GovCloud (US-West) region, bringing enterprise-grade agent capabilities to workloads with elevated compliance needs. AgentCore is a managed platform for building, deploying, and operating AI agents at scale without customers managing infrastructure. Its composable services—including Runtime, Gateway, Identity, Observability, and Evaluations—enable session isolation, long-running workloads, secure access to enterprise data via the Model Context Protocol, and integration with existing identity providers.

🚀 Amazon Bedrock AgentCore is now available in the AWS South America (São Paulo) Region. AgentCore provides a platform to build, connect, and optimize agents with runtime, identity, gateway, policy, observability, code interpreter, and browser tools available at launch. Customers can deploy agents closer to end users to reduce latency and meet data residency requirements, with security enforced at the infrastructure layer that agents cannot bypass.

🔐 Amazon Bedrock AgentCore Identity now supports On-Behalf-Of (OBO) token exchange, enabling developers to build agents that securely access protected resources on behalf of authenticated users without additional consent flows. The OBO exchange issues a new, scoped-down access token that carries both the user and agent identities, granting just-in-time, least-privilege access to outbound services. This capability is generally available in 14 AWS Regions.

🔧 Amazon announced a preview of optimization features for Bedrock AgentCore, adding automated recommendations plus batch evaluations and controlled A/B tests. These capabilities complete the observe–evaluate–improve loop by converting evaluation outputs and production traces into suggested system prompts and refined tool descriptions tailored to specific workloads. Batch evaluations validate recommendations against predefined test cases, while A/B tests measure impact on held-out or live traffic with statistical significance before changes are promoted and only after user approval.

🧩 Amazon Quick has introduced preview Microsoft 365 extensions for Excel, PowerPoint, and Word that let the service perform tasks directly inside users’ Microsoft 365 environments. The Excel extension supports complex spreadsheet analysis including pivot tables, charts, and data import/cleaning. PowerPoint enables template-driven deck creation and refinement from Quick data, while Word gains formatted document generation, sweeping edits with track changes, and reviewer participation in comments. The extensions are available in multiple AWS regions for early access.

🛡️ This article outlines AWS guidance for integrating trust, safety, and responsible-AI practices into applications built on Amazon Bedrock. It defines core responsible AI dimensions—such as safety, controllability, fairness, explainability, security and privacy, robustness, governance, and transparency—and maps them to lifecycle stages: design, deployment, and operations. It recommends observability and guardrail tools like Amazon CloudWatch and Bedrock Guardrails for monitoring, abuse detection, configurable content filters, and hallucination controls, and describes an abuse response process for coordination with AWS Trust & Safety.

🚀 Amazon Bedrock now includes OpenAI GPT OSS (120B and 20B) and NVIDIA Nemotron models (Nano 9B v2, Nano 12B v2, Nano 30B, Super 120B), enabling developers to access open-weight foundation models through a single API. The integration is powered by Mantle, a distributed inference engine that provides serverless, high-performance inference, unified capacity pools, automated quota management, and OpenAI API compatibility. These models are available on AWS GovCloud (US) for compliant, enterprise-grade deployments.

🚀 Amazon announced that Amazon Bedrock now provides access to the latest OpenAI models, Codex, and a Managed Agents offering in limited preview. OpenAI models and Codex integrate with Bedrock controls such as IAM, AWS PrivateLink, encryption, and CloudTrail, and usage can be applied toward existing AWS cloud commitments. Managed Agents run on Bedrock AgentCore, log actions per agent, and keep inference within the customer's AWS environment.

🔒 AWS has announced general availability of the AWS for SAP MCP Server on Amazon Bedrock AgentCore, enabling AI agents to connect directly and securely to SAP ERP systems at scale. Built on Model Context Protocol (MCP) and SAP OData standards, the server supports CRUD access to sales orders, purchase orders, materials, and finance documents. The managed AgentCore Runtime provides session isolation, private connectivity, and dual-layer authentication with CloudWatch telemetry and CloudFormation templates for rapid, no-infrastructure deployment.

🔍 AWS has extended Elastic Beanstalk's AI-powered environment analysis to Windows Server platforms, enabling developers and operators to diagnose and resolve Windows-based environment issues more quickly. The feature collects recent events, instance health metrics, and logs from Windows instances and sends that telemetry to Amazon Bedrock for analysis. You can request an AI analysis from the Elastic Beanstalk console using the AI Analysis button or programmatically via the AWS CLI with the RequestEnvironmentInfo and RetrieveEnvironmentInfo operations. Results include step-by-step troubleshooting recommendations tailored to the environment's current state and are available in Regions where both services are offered.

🚀 Amazon Bedrock AgentCore introduces a managed harness (preview), an AgentCore CLI, and prebuilt skills to help developers build and iterate on agents faster. The managed harness runs the complete agent loop in a per-session microVM with filesystem and shell access, supports model-agnostic switching, and lets teams export orchestration as Strands-based code. Filesystem persistence (preview) enables suspending and resuming sessions, and the CLI integrates with AWS CDK to deploy agents with governance and audibility.

🔎 AWS Deadline Cloud now includes an AI-powered troubleshooting assistant that analyzes failed render jobs to diagnose root causes and recommend fixes. The assistant examines logs and metrics for issues like missing assets, software errors, configuration mismatches, and resource constraints, drawing on a pre-trained knowledge base covering Deadline Cloud and popular DCC apps. It runs inside your AWS account via Amazon Bedrock and is available in all regions that support Deadline Cloud.

🚀 Claude Opus 4.7 is now available in Amazon Bedrock, delivering Anthropic’s most capable Opus release with improvements across coding, professional knowledge work, visual understanding, and long-running task handling. Served via Bedrock’s next-generation inference engine, Opus 4.7 offers enterprise features such as zero operator data access, dynamic traffic routing, and improved scalability. The model enhances agentic coding, systems engineering, long-horizon reasoning, and high-resolution image support, and is available in select AWS Regions.

🔍 Amazon Bedrock now supports cost allocation by IAM principal in AWS Cost and Usage Report 2.0 (CUR 2.0) and Cost Explorer. Customers can tag IAM users and roles with attributes like team, project, or cost center, activate those tags as cost allocation tags, and either include caller identity in a CUR 2.0 export or filter by tags in Cost Explorer. This capability is available in all AWS commercial Regions where Amazon Bedrock is offered.

🔐 Unit 42 found the AgentCore starter toolkit auto-creates overly permissive IAM roles that grant wildcard access to Bedrock AgentCore and ECR resources. The default deployment enables an “Agent God Mode” scenario where a compromised agent can exfiltrate container images, retrieve other agents’ MemoryIDs, invoke code interpreters, and read or poison memories across an entire AWS account. AWS updated documentation to warn these roles are intended for development; Unit 42 recommends creating scoped, least-privilege roles and auditing ECR, memory, and invoke permissions.

🖱️ Amazon announced that Bedrock AgentCore Browser now supports OS-level interaction capabilities to automate browser workflows beyond the Chrome DevTools Protocol (CDP). The update adds mouse and keyboard operations, full desktop screenshots, and handling for native system dialogs and print flows. It targets AI agent developers, test automation engineers, and teams building LLM-powered web interaction tools. The feature is enabled by default across all AgentCore Browser instances in the 14 supported AWS Regions.

🛡️ At AWS, decades of scaled security operations combine with new AI collaborations to proactively harden critical systems. Through Project Glasswing and Anthropic’s Claude Mythos Preview, AWS runs continuous AI-driven code reviews and provides gated research previews via Amazon Bedrock. Complementary offerings include AWS Security Agent for autonomous penetration testing and Bedrock guardrails and Automated Reasoning to enforce enterprise controls and reduce risk.

🔒 Amazon Bedrock now offers Claude Mythos Preview in a gated research preview as part of Project Glasswing. Anthropic's most advanced model to date demonstrates state-of-the-art capabilities across cybersecurity, software coding, and complex reasoning, identifying sophisticated vulnerabilities and showing exploitability in large codebases with less manual guidance. Access is limited to an allow-list in US East (N. Virginia) through Bedrock; AWS account teams will contact approved organizations.