All news with #amazon bedrock tag

🔧Amazon Quick now offers enhanced connector controls and Model Context Protocol (MCP) synchronization for connectors. Admins and connector owners can selectively enable or disable individual tools within a connector and configure tool permission settings to require consent or delegate decisions to end users. MCP sync ensures connectors stay up to date as external MCP servers add or modify tools and metadata. These updates are available in all Regions where Amazon Quick is offered.

🟢 AWS Config now supports 60 additional AWS resource types across services such as Amazon Bedrock, Amazon EC2, Amazon SageMaker, and AWS Organizations. If recording for all resource types is enabled, AWS Config will automatically start tracking these resources. The new types are available for use in Config rules and Config aggregators, enhancing discovery, assessment, auditing, and remediation across Regions.

🛠️ Amazon Quick is now generally available, enabling users to create custom applications by describing them in natural language. It connects to existing systems like Salesforce, Jira, Microsoft 365, databases, and data warehouses while honoring identity and access controls. Apps update automatically as source data changes and can be published to specific users or an entire organization. Available to Plus, Professional, and Enterprise customers starting September 1, 2026.

🔒 Amazon Bedrock AgentCore Identity now includes a managed consent portal that removes the need for custom OAuth callback infrastructure when connecting agents to third-party services. The portal is provided per AgentCore Gateway with a hosted web client and credential provider list, enabling platform admins to share a consent URL and users to self-service view connection status. The feature supports agent IDE-based clients that cannot natively handle OAuth consent flows and is available in all commercial regions where Bedrock AgentCore Identity is offered.

🔒 Anthropic's Claude Fable 5.1 is now generally available on Amazon Bedrock in AWS GovCloud (US), bringing frontier-level intelligence to regulated industry customers. The model is optimized for long-running, high-stakes tasks across coding, scientific research, and enterprise workflows. Anthropic designates Fable 5.1 as a Covered Model with enhanced data retention and safety policies, and AWS offers Enterprise Frontier Safeguards to let eligible customers keep data in their controlled cloud environments.

🆕 Amazon Timestream for InfluxDB is now available in eight additional AWS Regions including Cape Town, Bangkok, Hong Kong, Hyderabad, Melbourne, Seoul, Zurich, and Tel Aviv. Timestream for InfluxDB provides fully managed InfluxDB databases with Multi-AZ high availability, read replicas, enhanced durability, and multi-node scaling to support real-time time-series applications. You can deploy and manage databases via the console, AWS CLI, or AWS SDKs.

🔍 Amazon OpenSearch Service added 17 new Cluster Insights that diagnose root causes of Red and Yellow cluster status and offer actionable remediation steps. The insights cover resource exhaustion (JVM OOM, sustained CPU saturation) and configuration problems (zone imbalance, misconfigured replica counts). They automatically identify affected nodes and recommend fixes like resizing instances, increasing disk capacity, or correcting shard allocation.

🔒 Amazon Bedrock’s AgentCore Memory now supports fine-grained access control (FGAC), allowing per-user and per-tenant memory isolation via AgentCore Gateway without custom authorization code. Administrators can configure OAuth (JWT) authentication and attach Cedar policies to restrict access by caller identity, namespace claims, or specific Memory operations. The feature moves access enforcement into the infrastructure using cryptographic identity proof, and is implemented through the managed AgentCore Memory connector exposing 12 Memory operations as Cedar actions.

🧭 Amazon Bedrock AgentCore Memory now supports flexible namespace variables that let developers scope long-term memories along custom application dimensions such as organization, tenant, team, or environment. Define up to five keys on a memory resource, reference them in a strategy's namespace template, and supply values at runtime via the CreateEvent API so the service substitutes them during memory extraction. The feature helps multi-tenant and complex-hierarchy applications avoid duplicate strategies and provides fine-grained control over memory organization and access. Flexible namespace variables are available today in all Regions where AgentCore Memory is generally available, at no additional cost.

🚀 Amazon Bedrock in AWS GovCloud (US) now supports SpaceXAI Grok 4.6, a flagship model designed for coding, agentic tasks, and knowledge work. Grok 4.6 provides a 500k context window and configurable reasoning efforts (low, medium, high, xhigh). The model is accessible via the bedrock-runtime endpoint (Responses, Chat Completions, Converse APIs) and bedrock-mantle in GovCloud (US-East), with cross-Region inference routing for scaled access. Review the model card in the Amazon Bedrock User Guide to get started.

🚀 NVIDIA's Cosmos3-Edge, Cosmos3-Nano, and Cosmos3-Super are now available in Amazon SageMaker JumpStart, expanding AWS's foundation model offerings for physical AI. These omnimodal world models enable robots, autonomous vehicles, and vision AI to perceive, reason, plan, and act. Customers can deploy the models from the SageMaker JumpStart catalog or use the SageMaker Python SDK for integration.

🔔 Amazon Redshift now accepts Amazon Kinesis Data Streams (KDS) records up to 10 MiB, a tenfold increase from the prior 1 MiB limit. This update lets teams stream much larger payloads directly into Amazon Redshift without splitting records, simplifying ingestion pipelines and enabling new high-volume, large-record use cases. The feature is available now in all commercial AWS regions where Amazon Redshift is offered.

🚀 Amazon Bedrock AgentCore is now available in US West (N. California) and Asia Pacific (Hyderabad), enabling developers to build and run agents closer to end users. The platform supports agent runtime, identity and access control, policy management, session persistence, tool connectivity, evaluations, and observability at launch. AgentCore emphasizes secure infrastructure-level enforcement so agents cannot bypass controls. Regional availability reduces latency and improves performance for local customers.

🛠️ Amazon Elastic VMware Service (Amazon EVS) now supports the i7i.metal-48xl bare-metal Amazon EC2 instance, providing a higher core-count option with 5th generation Intel Xeon Scalable processors. This instance class delivers up to 23% better compute and >10% better price performance versus i4i instances, plus larger memory and storage to host more VMs per EVS host. The feature is available in Regions where both Amazon EVS and EC2 i7i are offered and enables VCF 9.x capabilities and onboarding automations.

🛡️ This post shows how to extend Amazon Bedrock Guardrails beyond the model boundary to tool calls and external data flows using the Strands Agents SDK lifecycle hooks. It explains three validation checkpoints—BeforeInvocationEvent, BeforeToolCallEvent, and AfterToolCallEvent—that run without changing agent or tool logic. The guide includes implementation details using boto3 and a reusable GuardrailHook that can be scoped per tool and deployed to Bedrock Agent Core Runtime. Examples and testing steps help validate guardrail behavior.

🤝 Amazon Bedrock now offers OpenAI's GPT-5.6 family — Terra and Luna — in AWS GovCloud (US-West) and (US-East), delivered via Bedrock's next-generation inference engine for security and high performance. Terra balances capability and cost while Luna prioritizes fast, low-cost inference; both support 1 million token context windows and prompt caching with explicit breakpoints for reduced billing on repeated context. Use the Bedrock Console or Responses API on the bedrock-mantle endpoint to get started.

🔔 Amazon Bedrock announces reduced pricing for OpenAI GPT-5.6 Sol, reflecting OpenAI's API price cuts. Sol now costs $4 per million input tokens and $20 per million output tokens, representing a 20% reduction on input and a 33.3% reduction on output pricing. The promotional rates apply at least through November 21, 2026, making high-volume, agentic coding and research workflows more cost-effective.

🛡️ Wazuh introduces AI-assisted capabilities to help Security Operations Centers reduce alert fatigue and accelerate investigations. The Wazuh AI Analyst on Wazuh Cloud delivers automated, scheduled security reports using Amazon Bedrock and Anthropic’s Claude, with encrypted processing and no model training on customer data. Self-deploy options include local Llama 3 via Ollama and FAISS-backed vector search for private threat hunting, while cloud-hosted Claude 3.5 Haiku can be integrated through OpenSearch Assistant for conversational guidance.

🧭 Amazon Bedrock AgentCore Memory now accepts non-conversational JSON payloads on the CreateEvent API, enabling extraction of long-term memories from structured data. Developers can submit JSON events up to 100 KB—such as behavioral events, activity logs, and system events—without converting them into synthetic conversations. The pipeline applies all four extraction strategies: semantic, user preference, summarization, and episodic, and the feature is available now in all supported regions.

🔍 Amazon Aurora DSQL introduces a CloudWatch Database Insights metric that provides per-statement, cluster-level performance monitoring. The feature captures sampled wait states and normalized SQL statements for active sessions, helping diagnose performance issues and identify resource-heavy queries. Metrics are collected at 1-minute intervals, available by default at no additional cost, and usable with CloudWatch Database Insights, CloudWatch PromQL, and the Aurora DSQL system diagnostics AI skill.