Amazon has published a reference architecture for connecting Bedrock AgentCore to private REST APIs and MCP servers in restricted network environments. By utilizing a VPC Lattice resource gateway placed in a dedicated network-account VPC, traffic between agents and internal tools is forced through a central inspection firewall.
AWS details three strategies to manage massive JSON payloads (20MB+) in AI agents, achieving up to 71% fewer tokens and 80% lower latency. The approach involves offloading state to Amazon S3, paginating large tool results, and compacting dictionary outputs.
Amazon has published a security guide for exposing AI agents via Bedrock AgentCore Runtime, emphasizing the need for robust ingress controls. The guide details how to prevent cross-tenant leakage and privilege escalation using identity propagation and layered authorization.
AWS has detailed three OAuth configurations for connecting AI agents running on Amazon Bedrock AgentCore to Snowflake-managed MCP servers. These patterns enable secure, per-user, or shared-service authentication between agentic layers and Snowflake Cortex tools.
Amazon has introduced new AI-driven data preparation capabilities within SageMaker to streamline the creation and maintenance of high-quality training and evaluation datasets. These features include auto-labeling, synthetic data generation, and automated data quality checks, controllable via Python SDK or AI-ML coding agents.
Aionic Labs has launched OpenTSLM-Flamingo, a time-series language model (TSLM) now deployable via Amazon SageMaker JumpStart. It combines the Gemma 3 4B architecture with a time-series encoder to interpret operational metrics alongside text context.
AWS now provides managed support for NVIDIA Dynamo within SageMaker HyperPod, simplifying the deployment of large-scale language models. This update introduces multi-node inference, allowing teams to run models that exceed single-GPU memory through disaggregated prefill and decode worker pools.
Amazon SageMaker AI has launched a new 'KV_AWARE' routing strategy that directs LLM inference requests to instances based on their actual KV cache state rather than just prompt headers. This optimizes multi-turn conversations and long-context workloads by ensuring requests land where relevant data is already cached.
AWS introduced the Social Messaging Agent Runtime Toolkit (SMART), an open-source SDK and Terraform stack designed to manage the complexities of WhatsApp integrations for AI agents built on Amazon Bedrock AgentCore. It handles authentication, media processing, conversation memory, and 24-hour message window constraints automatically.
Amazon has published a three-phase roadmap to help platform and application teams operationalize Responsible AI for agentic systems. It addresses the challenges of nondeterministic behavior, data boundary isolation, and regulatory compliance as agents move from pilot to production.
Amazon Bedrock has launched a new memory-aware capability for AgenticRetrieveStream. This feature automates the storage, extraction, and retrieval of user-specific facts and conversation histories, allowing agents to provide context-aware responses while maintaining strict document-level access control.
MoEngage has integrated AI agents into its customer engagement platform by using the Model Context Protocol (MCP) and Amazon Bedrock AgentCore to expose existing APIs as agent-callable tools. By treating its platform as an architecture of isolated sessions and standardized tool schemas, the company enabled teams to automate workflows and decision-making within a single conversation.
Amazon Bedrock Managed Knowledge Base now supports tabular search, allowing agents to process data directly from CSV, XLSX, and XLS files. The system uses model-written code in a secure sandbox to perform calculations and lookups across entire files, combining the results with facts from unstructured documents to provide comprehensive answers.
Amazon has released a reference architecture that integrates the NVIDIA NeMo Switchyard library with LiteLLM to dynamically route coding agent requests between different models on Bedrock. By using stage or random routing, you can shift traffic between high-capability and high-efficiency models to balance performance and cost.
Amazon has added OpenFold3-preview to SageMaker JumpStart, allowing users to deploy models for predicting 3D structures of proteins, DNA, RNA, and ligands. The implementation utilizes asynchronous inference endpoints to handle long-running predictions while supporting cost-efficient autoscaling and scale-to-zero capabilities.
Amazon Threat Intelligence observed autonomous agents using the open-source ARTEX framework to conduct large-scale credential theft and deepfake-based identity fraud. These campaigns exploited unpatched AI infrastructure and public misconfigurations to automate multi-stage offensive operations.
Amazon has released SGLang-Neuron, a plugin allowing developers to run large-scale AI models on AWS Trainium hardware using the standard SGLang interface. This integration enables native PyTorch execution and supports advanced features like PD disaggregation over EFA for optimized serving.
Amazon has released a next-generation runtime for Bedrock AgentCore designed to handle complex, long-running AI agent workloads. The update brings hardware-isolated environments with faster startup times, increased compute capacity, and improved cost efficiency through usage-based billing.
Amazon introduced a pattern for securing multi-tenant AI agents by ensuring that RAG search queries are scoped to specific users. The solution uses ACL-aware knowledge bases combined with a request interceptor in the AgentCore Gateway to deterministically inject verified user identities into tool calls, preventing LLMs or prompt injections from accessing unauthorized data.
Amazon introduced a framework for identifying silent data corruption (SDC) in distributed training, where faulty hardware returns incorrect math without triggering standard error logs. By integrating three custom checks—gradient sanity checks, ring replay audits, and weight fingerprinting—into PyTorch DDP training loops, you can identify, isolate, and replace failing nodes.
Amazon now offers a direct Web Search API for Bedrock AgentCore, enabling developers to perform web searches via standard AWS SDKs and CLI. This bypasses the need for the AgentCore Gateway, simplifying the process for custom agent loops and non-agent applications that require real-time information.
AWS has published a guide on creating an event-driven architecture to automatically sync Model Context Protocol (MCP) tool schemas with the AWS Agent Registry. Using AWS CloudTrail, EventBridge, and Lambda, this pipeline detects runtime changes and updates the registry whenever an MCP server's tool schema evolves.
Amazon has released the Universal Agent Evaluation Framework (UAEF), an open-source tool designed to standardize the evaluation of AI agents. It uses adapters to normalize execution traces from various frameworks like LangChain and LangGraph into a single format, enabling consistent measurement across 36 metrics and 7 quality dimensions.
Amazon has enabled usage-based software metering for bidirectional streaming models on SageMaker AI. Previously, software charges for long-running streaming sessions were difficult to capture, as they could not be reconciled with simple HTTP response headers. Model providers can now report usage incrementally via a dedicated metadata WebSocket connection.