roxsross

@roxsross.bsky.social

1 day ago

🛡️ Controla la seguridad de tu IA en AWS desde un solo lugar

aws.amazon.com/blogs/aws/amazon-bedrock...

#AWS #AmazonBedrock #IA #Seguridad

AWS News Feed on 🦋

@awsrecentnews.bsky.social

1 day ago

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.

🆕 Amazon Bedrock Guardrails enforces safety controls across all AWS accounts, blocking harmful content and hallucinated responses. Central teams can implement uniform protections from a single account, boosting efficiency. Available globally.

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

1 day ago

Introducing OpenClaw on Amazon Lightsail to run your autonomous private AI agents

AWS launches OpenClaw on Amazon Lightsail to run OpenClaw instance, pairing your browser, enabling AI capabilities, and optiona...

#AWS #AmazonBedrock #AmazonLightsail #ArtificialIntelligence #Compute #Launch #News

AWS News(Unofficial)

@awsnews.bsky.social

1 day ago

Amazon Bedrock Guardrails supports cross-account safeguards with centralized control and management

Organizational safeguards are now ge...

#AWS #AmazonBedrock #AmazonBedrockGuardrails #AmazonMachineLearning #ArtificialIntelligence #AwsOrganizations #Launch #News #Security #Identity #&Compliance

AWS News(Unofficial)

@awsnews.bsky.social

1 day ago

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 ...

#AWS #AmazonBedrock

AWS News Feed on 🦋

@awsrecentnews.bsky.social

4 days ago

Amazon Bedrock AgentCore Evaluations is now generally available Amazon Bedrock AgentCore Evaluations is now generally available, providing automated quality assessment for AI agents. Evaluations enables developers to monitor agent quality through continuous evaluation of production traffic, validate changes through testing workflows, and measure agent performance against defined expectations. AgentCore Evaluations offers two evaluation types. Online evaluation continuously monitors agent performance in production by sampling and scoring live traces. On-demand evaluation enables teams to test agents programmatically, supporting regression testing in CI/CD pipelines and interactive development workflows. Teams can evaluate agents using 13 built-in evaluators for response quality, safety, task completion, and tool usage. Developers can also use Ground Truth to measure agent performance against expectations, including reference answers for response validation, behavioral assertions for session-level goals, and expected tool execution sequences. For domain-specific requirements, teams can configure custom evaluators using their choice of prompts and model for LLM-based evaluation, or implement custom logic in Python or JavaScript through Lambda-hosted functions for code-based evaluation. Evaluations integrates with AgentCore Observability for unified monitoring and real-time alerts. AgentCore Evaluations is available in nine AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Europe (Frankfurt), Europe (Ireland). Learn more about Amazon Bedrock AgentCore Evaluations through the documentation, and get started with the AgentCore Starter Toolkit

🆕 Amazon Bedrock AgentCore Evaluations is now generally available, offering automated quality assessment for AI agents, continuous monitoring, and custom evaluators for response quality and task completion, available in nine AWS regions.

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

4 days ago

Amazon Bedrock AgentCore Evaluations is now generally available

Amazon Bedrock AgentCore Evaluations is now generally available, providing automated quality assessment for AI agents. Evaluations enables developers to monitor agent quality through continuous evaluation of p...

#AWS #AmazonBedrock

roxsross

@roxsross.bsky.social

6 days ago

🧠 Agentes con Memoria: Amazon Bedrock se vuelve 'Stateful'

openai.com/index/introducing-the-st...

#AmazonBedrock #IA #AgentesIA #AWS

AWS News Feed on 🦋

@awsrecentnews.bsky.social

1 week ago

Amazon Bedrock AgentCore Runtime now supports managed session storage for persistent agent filesystem state (preview) Amazon Bedrock AgentCore Runtime now offers managed session storage in public preview, enabling agents to persist their filesystem state across stop and resume cycles. Modern agents write code, install packages, generate artifacts, and manage state through the filesystem. Until now, that work was lost when a session stopped. With managed session storage, everything your agent writes to a configured mount path persists automatically, even after the compute environment terminates. When you configure session storage, each session gets a persistent directory at the mount path you specify. Your agent reads and writes files as normal, and AgentCore Runtime transparently replicates data to durable storage. When the session stops, data is flushed during graceful shutdown. When you resume with the same session ID, a new microVM mounts the same storage and the agent continues from where it left off — source files, installed packages, build artifacts, and git history all intact. No checkpoint logic, no save and restore code, and no changes to your agent application required. Session storage supports standard Linux filesystem operations including regular files, directories, and symlinks, with up to 1 GB per session and data retained for 14 days of idle time. Storage communication is confined to a single session's data and cannot access other sessions or AgentCore Runtime environments. Session storage is available in public preview across fourteen AWS Regions: US (N. Virginia, Ohio, Oregon), Canada (Central), Asia Pacific (Mumbai, Seoul, Singapore, Sydney, Tokyo), Europe (Frankfurt, Ireland, London, Paris, Stockholm). To learn more, see persist files across stop/resume in the Amazon Bedrock AgentCore documentation.

🆕 Amazon Bedrock AgentCore Runtime now supports managed session storage for persistent agent filesystem state in preview, enabling agents to retain files, packages, and artifacts across session stops and resumes without additional coding. Available in 14 AWS regions.

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

1 week ago

Amazon Bedrock AgentCore Runtime now supports managed session storage for persistent agent filesystem state (preview)

Amazon Bedrock AgentCore Runtime now offers managed session storage in public preview, enabling agents to persist their filesystem state across stop and re...

#AWS #AmazonBedrock

AWS News Feed on 🦋

@awsrecentnews.bsky.social

1 week ago

Amazon Bedrock AgentCore adds support for Chrome policies and custom root CA Amazon Bedrock AgentCore now enables customers to configure Chrome Enterprise policies for AgentCore Browser and specify custom root Certificate Authority (CA) certificates for both AgentCore Browser and Code Interpreter. These enhancements help ensure enterprise requirements are met when allowing AI agents to operate within organizations that have strict security policies and internal infrastructure using custom certificates. With Chrome policies, you can leverage over 100+ configurable policies for managing browser behavior across security, URL filtering, content settings, and more to enforce organizational compliance requirements. For example, restrict agents to specific URLs for kiosk-mode operations, disable password managers and downloads for data-entry tasks, or implement URL blocklists for regulatory compliance. Custom root CA support enables agents to seamlessly connect to internal services like Artifactory, Jira, and finance portals that use SSL certificates signed by your organization's internal Certificate Authority, and work with corporate proxies performing TLS interception. These features are available in all 14 AWS Regions where Amazon Bedrock AgentCore Browser and Code Interpreter are available: US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Paris), Europe (Stockholm), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Asia Pacific (Seoul), and Canada (Central). To learn more, visit the AgentCore Browser documentation.

🆕 Amazon Bedrock AgentCore now supports Chrome policies and custom root CA for enterprise compliance and secure internal service access in 14 AWS regions. Manage browser behavior and connect with custom certificates. For details, see the AgentCore Browser documentation.

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

1 week ago

AWS Weekly Roundup: Claude Sonnet 4.6 in Amazon Bedrock, Kiro in GovCloud Regions, new Agent Plugins, and more (February 23, 2026)

Last week, my team met many developers at Developer Week in ...

#AWS #AmazonAurora #AmazonBedrock #AmazonEc2 #AmazonNova #AmazonSagemaker #Launch #News #WeekInReview

AWS News(Unofficial)

@awsnews.bsky.social

1 week ago

Amazon Bedrock AgentCore adds support for Chrome policies and custom root CA

Amazon Bedrock AgentCore now enables customers to configure Chrome Enterprise policies for AgentCore Browser and specify custom root Certificate Authority (CA) certificates for both AgentCore Brow...

#AWS #AmazonBedrock

roxsross

@roxsross.bsky.social

1 week ago

🚀 Novedades AWS: Más potencia para Bedrock y SageMaker

aws.amazon.com/blogs/aws/aws-weekly-rou...

#AWS #AmazonBedrock #InteligenciaArtificial #Cloud

roxsross

@roxsross.bsky.social

1 week ago

🚀 AWS Weekly: Claude Opus 4.6, EC2 nuevas instancias y más novedades

aws.amazon.com/blogs/aws/aws-weekly-rou...

#AWS #CloudComputing #AmazonBedrock #TechNews

roxsross

@roxsross.bsky.social

1 week ago

🚀 AWS lanza nuevas instancias EC2 y modelos en Bedrock

aws.amazon.com/blogs/aws/aws-weekly-rou...

#AWS #CloudComputing #AmazonBedrock #Innovacion

roxsross

@roxsross.bsky.social

1 week ago

🚀 AWS Weekly: Claude Sonnet 4.6, Kiro en GovCloud y más novedades

aws.amazon.com/blogs/aws/aws-weekly-rou...

#AWS #AmazonBedrock #IA #Tech

roxsross

@roxsross.bsky.social

1 week ago

🚀 Novedades AWS: NVIDIA en Bedrock, Nova Forge y más

aws.amazon.com/blogs/aws/aws-weekly-rou...

#AWS #GenerativeAI #AmazonBedrock #TechNews

roxsross

@roxsross.bsky.social

1 week ago

🤖 Resumen Semanal AWS: NVIDIA Nemotron 3 Super en Amazon Bedrock, Nova Forge SDK y...

aws.amazon.com/blogs/aws/aws-weekly-rou...

#AmazonBedrock #GenerativeAI #AmazonCorretto #AWS #RoxsRoss

AWS News Feed on 🦋

@awsrecentnews.bsky.social

2 weeks ago

Amazon Bedrock AgentCore Runtime adds WebRTC support for real-time bidirectional streaming Amazon Bedrock AgentCore Runtime now supports WebRTC for real-time bidirectional streaming between clients and agents, adding to the existing WebSocket protocol support. With WebRTC, developers can build voice agents for browser and mobile applications that stream audio and video bidirectionally with low latency using peer-to-peer, UDP-based transport, enabling natural, real-time conversational experiences. WebRTC joins WebSocket as the second bidirectional streaming protocol supported by AgentCore Runtime. While WebSocket provides persistent, full-duplex connections for text and audio streaming over TCP, WebRTC is optimized for real-time media delivery where low latency is critical, such as voice agents in browser and mobile applications. WebRTC requires a TURN relay for media traffic, and AgentCore Runtime gives you flexibility in how you set that up: Amazon Kinesis Video Streams managed TURN for a fully managed experience with native AWS IAM integration, a third-party provider, or your own self-hosted TURN infrastructure. Both protocols benefit from AgentCore Runtime session isolation, observability, and scaling. WebRTC is supported in AgentCore Runtime across fourteen AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Canada (Central), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Paris), and Europe (Stockholm). To get started, see Bidirectional streaming in the Amazon Bedrock AgentCore documentation, which includes ready-to-deploy examples for both protocols: an Amazon Nova Sonic voice agent with KVS TURN server, Pipecat voice agents with WebSocket, WebRTC, and Daily transport, a LiveKit voice agent, and a Strands Agents SDK voice agent.

🆕 Amazon Bedrock AgentCore Runtime adds WebRTC for real-time, low-latency voice in browsers/mobile, complementing WebSocket. Choose managed TURN or self-hosted. Available in 14 regions. See documentation for examples.

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

2 weeks ago

Amazon Bedrock AgentCore Runtime adds WebRTC support for real-time bidirectional streaming

Amazon Bedrock AgentCore Runtime now supports WebRTC for real-time bidirectional streaming between clients and agents, adding to the existing WebSocket protocol support. With WebRTC,...

#AWS #AmazonBedrock

AWS News Feed on 🦋

@awsrecentnews.bsky.social

2 weeks ago

NVIDIA Nemotron 3 Super now available on Amazon Bedrock Amazon Bedrock now supports NVIDIA Nemotron 3 Super, an open hybrid Mixture-of-Experts (MoE) model designed for complex multi-agent applications. Built for agentic workloads, Nemotron 3 Super delivers fast, and cost-efficient inference enabling AI agents to maintain focus and accuracy across long, multi-step tasks without losing context. Fully open with weights, datasets, and recipes, the model supports easy customization and secure deployment, making it well-suited for enterprises, startups, and individual developers building multi-agent workflows, and advanced reasoning applications. Amazon Bedrock gives customers access to Nemotron 3 Super through a single, fully managed API — with no infrastructure to provision or models to host. Bedrock's serverless inference, built-in security controls, and compatibility with OpenAI API specifications make it easy to integrate Nemotron 3 Super into existing workflows and deploy at production scale with confidence. NVIDIA Nemotron 3 Super is now available in Amazon Bedrock across select AWS Regions. For the full list of available AWS Regions, refer to the documentation. To learn more and get started, visit the Amazon Bedrock console or the service documentation here. To get started with Amazon Bedrock OpenAI API-compatible service endpoints, visit documentation here.

🆕 Amazon Bedrock now offers NVIDIA Nemotron 3 Super, an open hybrid MoE model for complex multi-agent tasks. It provides fast, cost-efficient inference for AI agents, fully open for customization, and easy to deploy via Bedrock's managed API across select AWS Regions.

#AWS #AmazonBedrock

AWS News Feed on 🦋

@awsrecentnews.bsky.social

2 weeks ago

Minimax M2.5 and GLM 5 models now available on Amazon Bedrock Amazon Bedrock expands model selection for customers by adding support for GLM 5 and Minimax M2.5. GLM 5 is a frontier‑class, general‑purpose large language model optimized for complex systems engineering and long‑horizon agentic tasks. It builds on the GLM 4.5 agent‑centric lineage and is designed to support multi‑step reasoning, math (including AIME‑style benchmarks), advanced coding, and tool‑augmented workflows, with long context support suitable for sophisticated agents and enterprise applications. MiniMax M2.5 is an agent‑native frontier model trained explicitly to reason efficiently, decompose tasks optimally, and complete complex workflows under real‑world time and cost constraints. It achieves task completion speeds comparable to or faster than leading proprietary frontier models by combining high inference throughput with reinforcement learning focused on token‑efficient reasoning and better decision‑making in agentic scaffolds. MiniMax M2.5 and GLM 5 are now available in Amazon Bedrock across select AWS Regions. For the full list of available AWS Regions, refer to the documentation.

🆕 Amazon Bedrock now offers GLM 5 and Minimax M2.5 models for complex tasks. GLM 5 supports multi-step reasoning and coding; Minimax M2.5 optimizes task decomposition for efficient workflows. Available in select AWS Regions.

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

2 weeks ago

NVIDIA Nemotron 3 Super now available on Amazon Bedrock

Amazon Bedrock now supports NVIDIA Nemotron 3 Super, an open hybrid Mixture-of-Experts (MoE) model designed for complex multi-agent applications. Built for agentic workloads, Nemotron 3 Super delivers fast, and cost-e...

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

2 weeks ago

Minimax M2.5 and GLM 5 models now available on Amazon Bedrock

Amazon Bedrock expands model selection for customers by adding support for GLM 5 and Minimax M2.5. GLM 5 is a frontier‑class, general‑purpose large language model optimized for complex systems engineering an...

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

2 weeks ago

AWS Weekly Roundup: Amazon EC2 M8azn instances, new open weights models in Amazon Bedrock, and more (February 16, 2026)

I joined AWS in 2021, and since then I’ve watched the Amazon Elastic ...

#AWS #AmazonBedrock #AmazonElasticKubernetesService #AmazonOpensearchService #AmazonRds #WeekInReview

AWS News Feed on 🦋

@awsrecentnews.bsky.social

2 weeks ago

Amazon Bedrock AgentCore Runtime now supports shell command execution Amazon Bedrock AgentCore Runtime now supports InvokeAgentRuntimeCommand, a new API that lets you execute shell commands directly inside a running AgentCore Runtime session. Developers can send a command, stream the output in real time over HTTP/2, and receive the exit code — without building custom command execution logic in their containers. AI agents often operate in workflows where deterministic operations such as running tests, installing dependencies, or executing git commands need to run alongside LLM-powered reasoning. Previously, developers had to build custom logic inside their containers to distinguish agent invocations from shell commands, spawn child processes, capture stdout and stderr, and handle timeouts. InvokeAgentRuntimeCommand eliminates this undifferentiated work by providing a platform-level API for command execution. Commands run inside the same container, filesystem, and environment as the agent session, and can execute concurrently with agent invocations without blocking. Executing shell commands in AgentCore Runtime is supported across fourteen AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Canada (Central), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Paris), and Europe (Stockholm). To learn more, see Execute shell commands in AgentCore Runtime.

🆕 Amazon Bedrock AgentCore Runtime now supports shell command execution via InvokeAgentRuntimeCommand, enabling real-time output streaming and exit code retrieval without custom container logic. Available in 14 regions.

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

2 weeks ago

Amazon Bedrock AgentCore Runtime now supports shell command execution

Amazon Bedrock AgentCore Runtime now supports InvokeAgentRuntimeCommand, a new API that lets you execute shell commands directly inside a running AgentCore Runtime session. Developers can send a command,...

#AWS #AmazonBedrock

AWS News Feed on 🦋

@awsrecentnews.bsky.social

2 weeks ago

Amazon Bedrock AgentCore Runtime now supports the AG-UI protocol Amazon Bedrock AgentCore Runtime now supports the Agent-User Interaction (AG-UI) protocol, enabling developers to deploy AG-UI servers that deliver responsive, real-time agent experiences to user-facing applications. With AG-UI support, AgentCore Runtime handles authentication, session isolation, and scaling for AG-UI workloads, allowing developers to focus on building interactive frontends for their agents. AG-UI is an open, event-based protocol that standardizes how AI agents communicate with user interfaces. It complements the existing Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocol support in AgentCore Runtime. Where MCP provides agents with tools and A2A enables agent-to-agent communication, AG-UI brings agents into user-facing applications. Key capabilities include streaming text chunks, reasoning steps, and tool results to frontends as they happen; real-time state synchronization that can update UI elements such as progress bars and dashboards; structured tool call visualization that enables UIs to render agent actions transparently; and support for both Server-Sent Events (SSE) and WebSocket transport for bidirectional communication. AG-UI servers in AgentCore Runtime are supported across fourteen AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Canada (Central), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Paris), and Europe (Stockholm). To learn more, see Deploy AG-UI servers in AgentCore Runtime.

🆕 Amazon Bedrock AgentCore Runtime now supports AG-UI protocol for real-time agent experiences in user apps, handling auth, session isolation, and scaling. Available in 14 AWS regions, it complements existing protocols with streaming and real-time updates.

#AWS #AmazonBedrock

AWS News(Unofficial)

@awsnews.bsky.social

2 weeks ago

Amazon Bedrock AgentCore Runtime now supports the AG-UI protocol

Amazon Bedrock AgentCore Runtime now supports the Agent-User Interaction (AG-UI) protocol, enabling developers to deploy AG-UI servers that deliver responsive, real-time agent experiences to user-facing appli...

#AWS #AmazonBedrock