All news with #amazon bedrock tag

🔊 Amazon Bedrock AgentCore Runtime now supports WebRTC for low-latency, bidirectional streaming between clients and agents, enabling real-time audio and video in browser and mobile applications. WebRTC complements existing WebSocket support by providing peer-to-peer, UDP-based media transport optimized for voice agents and other media-intensive experiences. AgentCore Runtime supports managed TURN via Amazon Kinesis Video Streams, third-party providers, or self-hosted TURN, and the capability is available in 14 AWS Regions.

🔊 Amazon Web Services announced general availability of 10 new highly expressive Generative voices in Amazon Polly, covering eight locales including American, British, New Zealand, and Singapore English, plus French, Italian, German, and Swiss German. The Generative engine is now hosted in two additional regions — Europe (London) and Canada (Central) — and introduces a Bidirectional Streaming API. The new streaming capability lets customers send text and receive synthesized audio simultaneously, simplifying low-latency integrations with LLM-based systems for chatbots, game characters, and other real-time speech applications.

📢 AWS Database Migration Service (DMS) Schema Conversion with GenAI is now available in nine additional AWS Regions, enabling local processing and helping meet data residency requirements. The feature leverages Amazon Bedrock foundation models — including Claude 3.5 Sonnet v2, Claude 3.7 Sonnet, and Claude Sonnet 4 — to automate schema and code conversion. It converts schemas and code from Oracle, SQL Server, MySQL, PostgreSQL, and Sybase to Amazon Aurora PostgreSQL-Compatible Edition and Amazon RDS for PostgreSQL, reducing manual effort and accelerating migrations. DMS Schema Conversion is available at no additional charge and can be accessed through the AWS Management Console or CLI.

🔒 Amazon Bedrock AgentCore now lets administrators apply Chrome Enterprise policies to AgentCore Browser and upload custom root CA certificates for both AgentCore Browser and Code Interpreter. These capabilities enable enforcement of organizational controls such as URL restrictions, disabling downloads or password managers, and implementing URL blocklists while agents operate. Custom root CA support allows agents to connect to internal systems and work with corporate TLS interception without certificate errors. The features are available in 14 AWS Regions where AgentCore is offered.

📢 Amazon Bedrock now supports GLM 5 and Minimax M2.5, expanding its frontier model selection across select AWS Regions. GLM 5 targets complex systems engineering and long‑horizon agentic tasks, offering improved multi‑step reasoning, math (including AIME‑style capabilities), advanced coding, and long context support for sophisticated agents. Minimax M2.5 is agent‑native and optimized for efficient task decomposition, high inference throughput, and token‑efficient decisioning to deliver fast, cost‑sensitive task completion. Both models are available in Bedrock for enterprise and agentic workflows.

🚀 Amazon Bedrock now supports NVIDIA Nemotron 3 Super, an open hybrid Mixture-of-Experts (MoE) model designed for complex multi-agent and agentic workloads. The model delivers fast, cost-efficient inference for long, multi-step tasks while preserving context, and is released with open weights, datasets, and recipes for customization. Bedrock exposes Nemotron 3 Super via a single, fully managed, serverless API with built-in security controls and compatibility with OpenAI API specifications, and the model is available in select AWS Regions.

🔒 Researchers disclosed that Amazon Bedrock AgentCore Code Interpreter's sandbox mode permits outbound DNS queries, enabling attackers to create bidirectional command-and-control channels and exfiltrate data via DNS despite a "no network access" setting. BeyondTrust rated the issue 7.5/10 and recommends migrating critical workloads to VPC mode and using a Route53 DNS Firewall. Administrators should audit IAM roles and inventory active interpreters immediately.

⚙️ Amazon Bedrock AgentCore Runtime now supports InvokeAgentRuntimeCommand, an API that runs shell commands directly inside a running AgentCore Runtime session. The API streams stdout/stderr in real time over HTTP/2 and returns an exit code, removing the need for custom in-container command orchestration. Commands execute in the same container, filesystem, and environment as the agent session and can run concurrently with agent invocations. This capability is available in 14 AWS Regions.

🔒 BeyondTrust researchers demonstrated that the Sandbox mode in AWS Bedrock AgentCore Code Interpreter permits outbound DNS A/AAAA queries that can be abused to create a bidirectional covert channel. By encoding data in DNS requests and responses they showed both data exfiltration and an interactive reverse shell without triggering network restrictions. AWS reproduced the report but characterized the behavior as intended and updated documentation rather than issuing a patch.

🚀 Amazon Web Services has launched Amazon Bedrock in the Asia Pacific (New Zealand) Region, enabling customers to build and scale generative AI applications using a single API and a choice of foundation models. The managed service emphasizes built-in security, privacy, and responsible AI capabilities to support enterprise deployments. Models now available in New Zealand include Anthropic (Sonnet 4.5, 4.6; Opus 4.5, 4.6; Haiku 4.5) and Amazon’s Nova 2 Lite with cross-region inference support.

🤖 AWS announces general availability of AWS Partner Central agents, AI-powered agentic capabilities built on Amazon Bedrock AgentCore to accelerate partner co-selling. Agents provide pipeline insights, tailored sales plays, and next-step recommendations, and can populate CRM fields from transcripts, notes, and emails. They also identify funding eligibility, pre-fill funding requests, and are available in all commercial AWS Regions.

⚠️ Phantom Labs Research demonstrated a DNS-based exfiltration technique targeting the AWS Bedrock AgentCore Code Interpreter that bypasses expected Sandbox Mode network restrictions. Maliciously crafted files (for example, CSVs) can influence generated Python code to use DNS queries as a covert command-and-control channel. In tests, researchers executed commands, enumerated and retrieved S3 content and secrets while the environment still reported network access disabled. AWS says this is intended behavior and updated documentation; organisations should inventory AgentCore instances, tighten IAM roles and move sensitive workloads to VPC mode.

⚙️ Amazon Bedrock AgentCore Runtime now supports the Agent-User Interaction (AG-UI) protocol, enabling developers to deploy AG-UI servers that deliver real-time, interactive agent experiences into user-facing applications. AgentCore Runtime handles authentication, session isolation, and autoscaling for AG-UI workloads so teams can focus on building responsive frontends. AG-UI streams text, reasoning steps, and tool results over SSE and WebSocket and is available across fourteen AWS Regions.

🔔 Amazon announced that AgentCore Memory for Bedrock now supports streaming notifications for long-term memory, delivering push events to Amazon Kinesis whenever memory records are created or modified. Developers can subscribe to these streams to trigger downstream workflows, refresh application state, and build audit trails without polling. This reduces developer overhead and simplifies integration of personalized, memory-driven experiences. The feature is available in 15 AWS Regions.

🔔 Amazon Web Services has added stateful Model Context Protocol (MCP) server capabilities to Amazon Bedrock AgentCore Runtime, enabling server-driven elicitation, sampling, and progress notifications alongside existing support for resources, prompts, and tools. Developers can now run each session in an isolated microVM and preserve session context across interactions using an Mcp-Session-Id header. These features support interactive, multi-turn workflows and real-time updates for long-running operations.

🔍 Amazon Bedrock now emits two CloudWatch metrics: TimeToFirstToken and EstimatedTPMQuotaUsage. TimeToFirstToken measures latency from request submission to the first returned token for streaming APIs, enabling SLA baselines and latency alarms without client-side instrumentation. EstimatedTPMQuotaUsage estimates Tokens Per Minute consumption across Bedrock inference APIs to support proactive quota alarms and capacity planning.

🔍 AWS Elastic Beanstalk now offers AI-powered environment analysis that collects recent events, instance health, and logs and sends them to Amazon Bedrock for automated diagnosis. Developers and operations teams can request an analysis from the Elastic Beanstalk console or use the AWS CLI with RequestEnvironmentInfo and RetrieveEnvironmentInfo. The feature returns step-by-step, environment-specific troubleshooting recommendations to help reduce mean time to resolution and is available in Regions where both services exist.

🤖 Amazon Lightsail now lets you deploy OpenClaw, a private self-hosted AI assistant, on your own cloud infrastructure with simple, secure defaults. Each Lightsail OpenClaw instance includes built-in security controls—sandboxed agent sessions, one-click HTTPS for TLS, device-pairing authentication, and automatic snapshots—reducing manual configuration and operational risk. Amazon Bedrock is the default model provider, and users can swap models or connect to Slack, Telegram, WhatsApp, and Discord as needed.

🔒 Amazon has made Policy in Bedrock AgentCore generally available, providing centralized, fine-grained controls for agent-to-tool interactions. Teams can author policies in natural language that AWS converts into Cedar and stores in a policy engine attached to an AgentCore Gateway, which intercepts traffic and evaluates requests before allowing or denying access. Operating outside agent code, this lets security, compliance, and operations enforce access rules and validate inputs without modifying agents, improving governance and visibility across deployments.

🔁 Amazon Bedrock batch inference now accepts the Converse API as a model invocation type, letting you submit batch inputs in a consistent, model-agnostic Converse request format and receive outputs in the Converse response format. This unifies real-time and batch request formats, simplifying prompt management and reducing the effort of switching between models. You can configure the Converse invocation type through the Bedrock console or API, and the capability is available in all Regions that support Bedrock batch inference.