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.
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.
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.
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.
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.
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 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.
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.
Amazon Bedrock AgentCore now includes a comprehensive catalog of built-in, third-party, and custom evaluators to monitor agent behavior in production. The platform allows you to run metrics from DeepEval and AutoEval in a managed environment, supporting on-demand, online, and batch evaluation workflows.
Amazon introduced Mitra-v2, a tabular foundation model trained entirely on synthetic data. This version improves upon its predecessor by scaling the pretraining data size and introducing a hybrid structural causal model prior to better reflect real-world data relationships.
Amazon has expanded the capabilities of the AgenticRetrieveStream API, allowing developers to specify the iteration level for knowledge base requests. You can now choose between zero, one, or multiple retrieval steps to balance speed, cost, and complexity per request.
Amazon introduced a seven-layer reference architecture to move AI agent applications from initial prototypes to production-ready systems. The framework emphasizes a modular, pluggable design using stable contracts between layers such as data, inference, orchestration, and security.
Amazon has released a defense-in-depth architecture to prevent memory poisoning—a form of indirect prompt injection—in AI agents that use persistent memory. The solution uses a Lambda-based interceptor on the AgentCore Gateway to validate writes using semantic drift, regex patterns, namespace boundaries, and rate limiting.
Amazon SageMaker Inference has introduced support for NVIDIA Multi-Instance GPU (MIG), allowing you to partition a single physical GPU into multiple independent units. This hardware-level division provides dedicated compute and memory to each partition, ensuring predictable latency and strong isolation between models hosted on the same accelerator.
Taxbit has deployed a secure, role-aware AI assistant using Amazon Bedrock AgentCore to automate product documentation support. The agent uses RAG to ground answers in verified content while strictly enforcing PII masking, regional data residency, and user-role permissions.
Amazon introduced a serverless Model Context Protocol (MCP) gateway built on Amazon ECS Fargate that allows AI agents to query enterprise data lakes using a metadata-driven approach. Instead of writing custom integration code for every new dataset, you define table schemas and business logic in JSON, which the system automatically registers and indexes.
Amazon introduced Web Answer on Bedrock AgentCore, a managed tool that simplifies agent-based web research. It automates the entire pipeline from searching and verifying facts to synthesizing cited answers, delivering results via MCP.
Amazon Quick has launched Smart Approvals to automate routine agent tasks while maintaining human oversight for critical decisions. The system uses a classifier to evaluate requested actions against conversation context and user policy, preventing unnecessary interruptions without bypassing established security controls.
Amazon introduced a multi-agent system built on Bedrock AgentCore that automates engineering document evaluation and substitution. The architecture combines multimodal retrieval, deterministic Python-based tolerance checking, and hierarchical LLM orchestration.
Amazon has published a workflow for using Sequence-Level Knowledge Distillation (SeqKD) to fine-tune smaller models on trajectories generated by frontier models. By using a 'teacher' model to generate successful tool-use trajectories and filtering them with a programmatic scorer, teams can train compact 'student' models that perform complex reasoning at a fraction of the cost.
Amazon Bedrock AgentCore now supports Session endpoints, allowing developers to view and interact with web applications live as an AI coding agent builds them. By routing traffic through an authenticated, isolated microVM session, changes appear in the browser instantly without requiring separate deployments.
Amazon has enabled intent-driven UI automation by pairing Nova Act with the Bedrock AgentCore Browser Tool. This setup allows engineering teams to define test workflows through natural language instructions instead of maintaining rigid, selector-heavy codebases.
AWS has updated its QA Studio reference solution, adding native support for multi-team organizational structures. The new capabilities include application-level ownership, automated health scoring based on CloudWatch metrics, and granular role-based access control.
Amazon Bedrock now supports explicit and implicit prompt caching for OpenAI models, allowing you to store and reuse static prompt prefixes like tools, instructions, and conversation history. By avoiding the re-processing of identical tokens across turns, you can significantly lower input costs and improve responsiveness in complex agent workflows.
Amazon Bedrock AgentCore is a new service designed to streamline the deployment and management of multi-agent architectures. It handles agent hosting, secure tool access via MCP, and session isolation, enabling teams to focus on agent behavior rather than operational overhead.
Audible has developed a controllable text-to-speech pipeline that uses LLMs to profile characters and attribute dialogue with up to 97% accuracy. By providing 'stage directions' as natural-language captions, the system ensures distinct, consistent character voices over long-form content.
Amazon has released TorchNeuron, an open-source backend that lets existing PyTorch code run on AWS Trainium accelerators without major rewrites. The release introduces a new execution mode plus layered caching to reduce recompilation, and its reliability was validated through an AI-agent-driven testing pipeline that distilled hundreds of thousands of Hugging Face models down to a manageable benchmark set. Internal large-model tests reported roughly a 33% reduction in the delay before the first training step begins.
AWS has upgraded the Amazon Polly Generative engine with more natural, expressive speech and better accuracy for numbers, addresses and confirmation codes. The update adds 14 new voices across 9 locales, bringing the total to 57 generative voices in 11 languages and 25 locales, including first-time general availability for Hindi and Finnish. It is a drop-in upgrade: voice names, APIs and pricing stay the same, so existing applications work unchanged.
Amazon partnered with the independent nonprofit AVERI to audit the quality of its own internal safety-evaluation datasets for its AI models, not just the models' outputs. AVERI reviewed a random, anonymized sample of safety-test prompts covering areas like harmful content, cybersecurity, privacy and copyright. The review confirmed strong topical coverage, diverse testing methods and low contamination risk, but flagged gaps in multilingual coverage and multistep adversarial testing. Amazon responded with four concrete changes to its evaluation process.
Amazon Web Services researchers published a method called 'priming' that converts pretrained Transformer models into hybrid architectures mixing attention and state space model (SSM) layers, reusing existing weights instead of retraining from scratch. The approach cuts pretraining costs by over 99% and lets a 32-billion-parameter hybrid model match its source Transformer's quality while decoding up to twice as fast. Amazon tested three SSM types and released an open-source model zoo, training code, and serving tools under Apache 2.0.
AWS researchers describe a system that models telecom networks as a continuously updated graph ('digital twin') and uses AI agents to run a cascade of graph algorithms (decomposition, clustering, centrality ranking) to pinpoint root causes of failures. The approach was demonstrated with NTT DOCOMO at Mobile World Conference, reportedly cutting root cause analysis from hours to minutes on commercial networks. Agents also consult an incident knowledge base and runbooks, and can escalate autonomy from advisory to supervised to full remediation over time.