All news with #amazon bedrock tag

🔎 Today AWS expanded Amazon Bedrock's Web Search to support an external_web_access parameter, allowing models to fetch live public web content while preserving control over data egress. Grant the bedrock-websearch:ExternalWebAccess IAM permission to enable live fetches; leaving the parameter false restricts results to Amazon's in-AWS index. The capability is available in US East (N. Virginia), US East (Ohio), and US West (Oregon).

🔎 Amazon Bedrock's AgentCore Web Search now supports per-request domain filtering and published-date filtering, letting agents control which sites and time windows they search. Runtime domain filtering enables include/exclude lists for trusted or blocked sources without admin reconfiguration, while published-date filtering constrains results to specific inclusive date ranges. Admins gain gateway-level allowlists and an increased domain cap of up to 100 domains per list, and the Web Search Tool is expanding availability to eu-west-1 and ap-northeast-1.

🔍 AWS Cost Anomaly Detection now monitors spend for third-party foundation models on Amazon Bedrock, including provider-hosted models like Anthropic Claude. The service uses machine learning to detect and alert on unusual spend, and this update extends automatic anomaly detection to Bedrock model usage. Alerts include a ranked root-cause breakdown by dollar impact across service, account, Region, and usage type, and the feature is available in all commercial AWS Regions except GovCloud and China.

🛡️ This post demonstrates patterns for propagating user authorization context when building AI agents with Amazon Bedrock AgentCore, ensuring each user only sees data they’re allowed to access. It explains how to embed department or custom claims in tokens via Amazon Cognito pre token generation triggers and how the AgentCore Runtime inbound JWT authorizer validates those claims before invoking agent code. The guidance shows moving enforcement into infrastructure—using STS session tags, per-request AssumeRoleWithWebIdentity for DynamoDB, metadata filters for Bedrock Knowledge Bases, and on‑behalf‑of token exchange for external SaaS—to reduce risk from compromised agents.

🚀 Amazon Bedrock now supports SpaceXAI Grok 4.6, SpaceXAI's flagship model optimized for long-running agents and complex interactive and visual tasks. Grok 4.6 provides a 500K token context window and configurable reasoning efforts (low, medium, high, xhigh) to tailor performance. The model targets multi-step workflows such as research, code analysis, and application development, claiming frontier-level performance on agentic coding and knowledge benchmarks. With Bedrock integration, customers gain enterprise-grade security, monitoring, and cross-Region scalability for Grok 4.6 deployments.

🚀 Amazon Bedrock now supports OpenAI GPT-5.6 Terra and Luna in India with India Geo cross-Region inference. This feature ensures inferencing stays within India while automatically routing requests across AWS Regions like Mumbai and Hyderabad for higher throughput. The models run on the bedrock-runtime endpoint and support Responses, Chat Completions, and Converse APIs, integrating with existing account-level controls including model invocation logging and CloudWatch metrics.

🔒 This post explains how to implement a request Lambda interceptor in Amazon Bedrock AgentCore Gateway to support legacy HTTP Basic Authentication for downstream tool APIs. It shows retrieving a service account credential from AWS Secrets Manager, validating inbound JWTs, and constructing a Basic Auth header while keeping credentials isolated from the agent. The article emphasizes that Basic Auth is outdated and recommends modern authentication like OAuth 2.0 or OpenID Connect, presenting this pattern only as an interim integration.

🔔 Amazon Web Services announces general availability of AgentCore payments, part of Amazon Bedrock AgentCore, enabling AI agents to discover, access, and pay for paid APIs, MCPs, and content with minimal code. The capability integrates with Coinbase and Stripe Privy wallets, supports the Machine Payment Protocol (MPP), and offers payment orchestration, configurable infrastructure-level limits, and end-to-end observability. GA features include Quick Create for Coinbase credentials, a curated Coinbase Bazar MCP server of x402 pay-per-use endpoints, and support for the x402 "upto" scheme for dynamic pricing.

🤖 Amazon Bedrock now supports OpenAI GPT‑5.6 models (Sol, Terra, Luna) on the bedrock-runtime endpoint and adds cross‑Region inference. The feature includes Global and Geo routing (now with US Geo support) to increase throughput and reduce inference costs. OpenAI Responses, Converse, and Chat Completions APIs are supported and integrate with Bedrock logging, CloudWatch metrics, and AWS cost reporting.

🛡️ AWS GovCloud (US) now supports Claude Opus 5, the latest Opus model, with zero data retention (ZDR) enabled by default. The model is accessible via the bedrock-runtime endpoint in both GovCloud regions and via bedrock-mantle in GovCloud (US‑West). Claude Opus 5 improves coding, long-running agents, and complex document reasoning while maintaining regional data residency.

🔒 Security teams can now access Daybreak Red and Daybreak Blue from OpenAI on Amazon Bedrock. Daybreak Blue supports common defensive workflows like vulnerability discovery, detection engineering, and incident response, while Daybreak Red targets advanced, authorized tasks such as vulnerability research and exploit reproduction with stronger identity verification and monitoring. Both models run on Bedrock's next-generation inference engine with zero-operator access and do not use inference data for model training.

🔒 Amazon Bedrock now supports cost allocation by AWS Identity and Access Management (IAM) principal — including IAM users and roles — for model inference requests made through the bedrock-mantle endpoint. This extends existing support for the bedrock-runtime endpoint and enables customers to attribute inference costs to teams, projects, or applications using IAM principal tags. Activate IAM principal tags in the AWS Billing and Cost Management console to analyze costs in AWS Cost Explorer or include caller identity data in AWS Cost and Usage Report 2.0.

🔒 This post shows how to route Amazon Bedrock Guardrails intervention events into Amazon Security Lake by transforming model invocation logs into OCSF-compliant Detection Finding records. It outlines an automated pipeline using CloudWatch Logs subscription filters, an AWS Lambda transformer, Parquet output, and Security Lake partitions so analysts can query guardrail events alongside identity, network, and application telemetry. The solution maps guardrail fields to OCSF attributes, supports multi-account deployment, and offers scaling guidance and an alternative CloudWatch-only approach.

🛡️ Amazon Bedrock AgentCore introduces temporal policies for stateful agent authorization and rate limiting to control AI traffic. Temporal policies evaluate requests in the context of prior actions within a session, enabling workflow sequencing, exact argument matching, human approvals, and data freshness checks. Rate limiting provides per-user and per-group controls via OAuth or AWS IAM to cap requests, token usage, and concurrent connections for improved downstream availability. Documentation, a blog announcement, and the Dogwood reference implementation offer regional details and guidance.

🆕 Amazon Web Services announces general availability of native vector search for Amazon DynamoDB. The feature enables indexing and approximate nearest neighbor searches over embeddings with single-digit millisecond latency and 99%+ recall at any scale, including trillions of vectors. You can store embeddings alongside other attributes, choose a model to generate vectors (including Amazon Bedrock models), create vector indexes, and apply attribute filters. DynamoDB vector search preserves serverless benefits—no infrastructure management, zero downtime, and pay-as-you-go—supporting use cases such as agent memory retrieval, semantic search, recommendations, and personalized advertising.

🔎 Amazon Web Search on Amazon Bedrock is now generally available, providing a built-in server-side web search tool that enables OpenAI models to ground responses with current web knowledge while keeping data residency inside AWS and ensuring zero data egress. The feature eliminates the need for third-party search vendors, extra API keys, orchestration, and vendor security reviews by integrating via a single parameter in the existing API call and returning semantic snippets with citations.

🚀 GPT-5.6 Sol, Terra, and Luna on Amazon Bedrock now support 1 million token context windows, allowing full-codebase analysis, long-form document processing, and complete multi-turn histories in a single request. Models provide broader-context reasoning and more coherent outputs without chunking. Prompt caching with explicit cache breakpoints reduces repeated-context billing by 90%, and pricing aligns with OpenAI first-party rates. Availability varies by model across US East (N. Virginia and Ohio) and US West (Oregon) regions, accessible via the Bedrock Console or the Responses API on the bedrock-mantle endpoint.

🔔 AWS Config now supports 15 additional AWS resource types across services such as Amazon Bedrock, Amazon OpenSearch Serverless, and Amazon SageMaker. If recording for all resource types is enabled, AWS Config will automatically track these new additions. The new types are also available for use with Config rules and Config aggregators, improving discovery, assessment, audit, and remediation coverage across Regions where the resources exist.

📰 On July 30, OpenAI updated pricing for GPT-5.6 Terra and GPT-5.6 Luna, with GPT-5.6 Sol unchanged. Terra targets balanced production workloads with GPT-5.5-level performance at lower cost, while Luna is optimized for high-volume, low-latency inference and cost per token. Pricing on Amazon Bedrock now matches OpenAI first-party rates and usage counts toward existing AWS commitments.

🚀 xAI's Grok 4.3 is now available on Amazon Bedrock in AWS GovCloud (US‑West), adding another model provider option for government and regulated workloads. Grok 4.3 is a reasoning-first model with configurable reasoning effort and strong tool-use and instruction-following capabilities. It runs on the new Mantle inference engine to provide price-performance benefits, tool calling, structured output, and response streaming. The model is suited for enterprise scenarios like customer support, legal research, and financial Q&A.