All news with #amazon bedrock tag

🛡️ Amazon Bedrock Guardrails introduces the InvokeGuardrailChecks API, a resourceless endpoint that lets you apply individual safeguards at any step of agentic AI workflows without creating guardrail resources. The API returns numeric severity and confidence scores so you can set custom thresholds and actions — block, pass, retry, or log — per request. It supports content filters, prompt attack detection, and sensitive information filters and is available in multiple AWS Regions.

🔍 AWS Transform now provides a model-to-model migration custom transformation that evaluates generative AI workloads and generates a migration plan to Amazon Bedrock. The agent scans codebases to identify AI SDKs and models, collects migration requirements interactively, and maps models to Bedrock equivalents with cost comparisons and production-ready code changes. It preserves application architecture while recommending routing, caching, and Bedrock integrations for secure, consolidated deployment.

🚀 AWS announced that xAI’s Grok 4.3 is now available on Amazon Bedrock, making xAI a model provider on the platform. Grok 4.3 is a reasoning-first model with configurable, always-on reasoning levels and optimized token efficiency. It supports strong tool use, instruction following, and is suited for enterprise tasks like contract and financial document analysis. The model runs on Mantle, Bedrock’s new inference engine supporting tool calling and streaming.

📌 Amazon Bedrock AgentCore Memory now allows applications to attach metadata values directly to short-term memory events so those values are preserved exactly when converted into long-term memory records. Previously, metadata had to be inferred by the LLM during extraction. Setting a metadata key to STRICTLY_CONSISTENT ensures the provided value is unchanged, prevents merging across different values, and lets you group events for department scoping, compliance boundaries, and multi-tenant isolation. The feature supports up to three strictly consistent STRING keys per strategy and is available in all AWS Regions where AgentCore Memory is supported.

🔎 Amazon Bedrock AgentCore now offers Web Search generally available in US East (N. Virginia). The fully managed tool provides agents with current web knowledge, combining an Amazon-operated web index and structured knowledge graph data to return high-value excerpts, entity data, and verified facts. Web Search integrates with AgentCore via the Model Context Protocol (MCP) and keeps data residency within your secured AWS environment with zero data egress.

🚀 AWS has expanded availability of OpenAI's GPT-5.4 and GPT-5.5 models to the US East (N. Virginia) Region on Amazon Bedrock. These models support a 272K-token context window, accept text and image input, and are accessible via the Responses API with server- and client-side tool calling, projects, and response streaming. GPT-5.5 targets advanced coding, research, analysis, and long-running agentic tasks, while GPT-5.4 focuses on frontier reasoning, coding, tool use, and long-context workflows.

🚀 AWS announces availability of the Gemma 4 family from Google DeepMind on Amazon Bedrock. The offering includes three variants—Gemma 4 31B, Gemma 4 26B-A4B, and Gemma 4 E2B—covering dense and MoE architectures with multimodal and multilingual support. Models run on new Bedrock optimizations for tool calling, structured output, reasoning, and streaming, and are initially available in several AWS Regions.

🤖 Claude Fable 5 is now generally available on AWS, offering Mythos-level capabilities with built-in safety classifiers for broader use. The model advances autonomous knowledge work and coding for professional tasks across finance, legal, marketing, sales, data, and engineering. Customers can access it via Amazon Bedrock or the Claude Platform on AWS, with options for AWS-managed guardrails and regional data residency.

🔍 Amazon Connect Customer now provides AI agent traces for self-service voice interactions, letting operators inspect how AI agents reasoned, acted, and responded during conversations. The feature displays step-by-step traces alongside full transcripts in the Connect web UI so teams can confirm correct behavior, diagnose failures, or spot tool and parameter issues. It is available in all AWS Regions that support Amazon Connect Customer AI Agents and is documented in the Amazon Connect Customer Administrator Guide.

🖥️ Amazon Bedrock AgentCore Runtime introduces the InvokeAgentRuntimeCommandShell API, providing a persistent, PTY-backed terminal over WebSocket into running agent sessions. This complements existing one-shot execution via InvokeAgentRuntimeCommand and delivers a full terminal experience inside an isolated microVM with features like colors, tab completion, Ctrl+C, resize, and automatic reconnect. Developers hosting coding agents (for example, Claude Code, OpenAI Codex, Amazon Kiro) can now authenticate, drop into the agent microVM, inspect files, run ad-hoc commands, and debug while retaining session state across reconnects. Each interactive session uses a runtime session ID and shell ID for resume; up to 10 concurrent shells are supported per runtime.

🛠️ The Amazon Bedrock console has been redesigned to match real-world model development workflows: experiment, iterate, and scale. The refreshed UI centers on the bedrock-mantle endpoint and is compatible with the OpenAI Responses API, OpenAI Chat Completions API, and the Anthropic Messages API. Users can browse and compare models, create projects to run evaluations, and get project-aware code snippets prefilled with model ID, region, endpoint URL, and API key references. The new experience is available in all Regions where the bedrock-mantle endpoint is offered.

🤖 AWS Step Functions now integrates with the Amazon Bedrock AgentCore managed harness (preview) to add AI agent reasoning steps to workflows. The integration lets you declare agents via configuration, run agents in parallel or sequence, add human approvals, and view execution history with agent inputs, outputs, token usage, and CloudWatch links. You can reuse or create harnesses from Workflow Studio, apply per-invocation overrides, and persist agent context with session IDs. The harness preview and integration are available in select regions and standard Step Functions and Bedrock pricing applies.

🛡️ Amazon Bedrock now offers OpenAI GPT‑5.4 in AWS GovCloud (US‑West), enabling government and regulated industry customers to use OpenAI's most capable frontier model with the security and compliance of GovCloud. GPT‑5.4 delivers native computer-use capabilities and advanced reasoning across coding, documents, and multi-step agentic tasks, running on Bedrock's high-performance inference engine. Data remains in-partition and is not used to train models.

🔒 This post shows how SaaS providers can use Amazon Bedrock AgentCore resource-based policies to control multi-tenant access to a shared AgentCore Runtime and Runtime endpoint. It walks through two tenant scenarios: cross-account access for Example Corp and VPC-restricted access for AnyCompany, demonstrating how to apply resource-level Allow and explicit Deny conditions. The article covers required IAM permissions, example policy files, and verification steps to ensure network- and identity-based constraints are enforced.

🔒 Amazon Quick now supports connecting privately hosted Model Context Protocol (MCP) servers via Amazon Virtual Private Cloud (VPC). This enables organizations to integrate proprietary MCP servers running on Amazon EC2, AWS Fargate, AWS Agentcore, or other private compute without exposing them to the public internet. During connector creation, choose your VPC and provide your MCP server URL so teams can interact with private MCPs in Quick while traffic remains routed securely through the VPC.

🔐 Amazon Bedrock AgentCore Identity now lets customers reference existing AWS Secrets Manager secret ARNs directly in Credential Providers. Previously, secrets were service-managed and created by AgentCore Identity, limiting tagging, CMK encryption, and governance controls. Customers can now create and manage secrets with their own policies and then reference the ARN without changing runtime behavior. This feature is GA in 14 AWS Regions.

🟦 Amazon Bedrock customers can now monitor inference traffic to the bedrock-mantle endpoint using Amazon CloudWatch metrics, matching existing support for the bedrock-runtime endpoint and other AWS services. The bedrock-mantle endpoint supports OpenAI Responses and Chat Completions APIs as well as the Anthropic Messages API, enabling easy migration of OpenAI- or Anthropic-based applications to Bedrock. Metrics are published under the AWS/BedrockMantle namespace and include inference counts, token totals, and client error counts across account, project, model, and project-and-model granularities. These metrics are available in all Regions where the bedrock-mantle endpoint is offered and can be used to monitor production inference, set alarms, and plan capacity.

🚀 Amazon Bedrock now supports OpenAI GPT-5.5, GPT-5.4, and Codex for production use, offering the same AWS security, governance, and operational controls. GPT-5.5 delivers advanced capabilities for agentic coding, data analysis, and multi-step autonomous tasks on a next-generation inference engine. Codex is available via a dedicated App, CLI, and IDE integrations for Visual Studio Code, JetBrains, and Xcode, and can be configured to run through Bedrock with pricing aligned to OpenAI first-party rates.

🤖 AWS now offers Claude Opus 4.8, Anthropic's most capable generally available model, bringing advances in agentic coding, professional knowledge work, and autonomous long-running tasks for developers and enterprises. The model sustains longer sessions, reasons more deeply, and maintains consistency for production workflows. Customers can access Opus 4.8 via Amazon Bedrock or the Claude Platform on AWS, with AWS-managed features and unified billing.

🚀 Amazon Bedrock customers can now view inference quotas for the bedrock-mantle endpoint via AWS Service Quotas. This update surfaces per-model input-tokens-per-minute and output-tokens-per-minute limits, aligning visibility with existing bedrock-runtime and other AWS services. The feature is available in all Regions offering the endpoint and quota increases follow the standard Bedrock limit request process.