AWS Machine Learning Blog
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
AWS AgentCore: A Framework for Multi-Tenant AI Agents in SaaS
AWS unveiled the AgentCore framework for multi-tenant AI agents. The system addresses architectural challenges of data isolation, scaling, and managing multiple clients in SaaS applications.
AWS Deployed AI Agents to Optimize Radiologists' Workflows
Artificial intelligence is teaching hospitals to better distribute diagnostic studies among radiologists, solving the problem of diagnostic delays and physician burnout.
Amazon Nova Act Receives HIPAA Certification for Healthcare Applications
Amazon has added HIPAA compliance for Nova Act models, opening the path for using AI in healthcare applications with secure patient data processing.
Amazon Bedrock: Custom Lambda-evaluators for AI Agent Control
AWS showed how to integrate Lambda functions into Bedrock AgentCore for automatic validation of agent responses—from fact-checking to PII detection.
Amazon Bedrock Adds Three Ways to Manage AI Agent Tools
AWS Bedrock offers developers a choice between a Docker sandbox, managed Code Interpreter, and an Anthropic SDK-compatible proxy for calling tools from AI agents.
AWS accelerated ML pipelines in SageMaker Feature Store with three new capabilities
The AWS SageMaker Python SDK gained three new capabilities for managing ML data: integration with Lake Formation, support for Iceberg, and pipeline optimization.
AWS Bedrock AgentCore Memory: how to give AI agents long-term memory in Kiro CLI
AWS integrated long-term memory into Kiro CLI through Bedrock AgentCore Memory and a custom MCP server. AI agents in the terminal can now remember the context of previous interactions.
Amazon Nova Sonic: Three Architectures for Voice Agents
AWS showed how to build voice agents with Amazon Nova Sonic and Bedrock AgentCore. The article breaks down three architectural schemes and latency minimization tactics for interactive dialogues.
AWS SageMaker and vLLM: real-time streaming speech transcription
AWS SageMaker with vLLM enables real-time speech processing through a streaming architecture. Instead of waiting for a full recording, the system processes audio in chunks and delivers results instantly.
Multimodal judges: how AWS evaluates the quality of image descriptions
AWS has introduced a new way to evaluate AI models that describe images. Multimodal evaluators check whether a model actually relies on the content of the image.
Amazon SageMaker API: Full OpenAI-Compatible Support
Amazon SageMaker AI now supports an OpenAI-compatible API for real-time endpoints. Developers can use familiar tools by simply changing the endpoint URL.
Amazon Nova 2 for content moderation: a structured prompting approach
Amazon presented a prompting methodology for content moderation with Nova 2 Lite. Tests on three open datasets showed better results than other models.
Aderant accelerated Amazon Quick cloud operations 10x
Aderant unified search across six systems in the Amazon Quick cloud and sped up document search by 90%.
AWS Introduces Payments for AI Agents — Bedrock AgentCore Integration with Coinbase and Stripe
Amazon Web Services has introduced Amazon Bedrock AgentCore Payments — a new set of features that enables AI agents to autonomously make payments for the services they use.
Verifiable rewards: how AWS improves neural network training
AWS introduced the RLVR approach — training with verifiable rewards — which improves model accuracy on math tasks and code generation.
AWS launched hourly GPU reservations — for ML testing and release preparation
AWS introduced EC2 Capacity Blocks for ML, a service for quickly reserving GPU capacity by the hour instead of for months, aimed at load testing and model validation.
Halliburton sped up seismic workflows by 95% with Amazon Bedrock
Oil and gas company Halliburton developed an AI assistant based on Amazon Bedrock that converts natural language commands into seismic workflows, speeding up their creation 20x.
Databricks and AWS SageMaker: a pipeline for secure LLM fine-tuning
AWS and Databricks created a Unity Catalog integration with SageMaker for secure LLM fine-tuning while preserving data governance and lineage
AWS and Cisco address three AI agent security issues when scaling
The AWS and Cisco AI Defense partnership addresses visibility, security, and compliance issues when deploying large numbers of AI agents at the enterprise level through automated scanning and a unified management system.
Amazon Nova Sonic: how to build real-time voice streaming applications
AWS has published a detailed guide to building voice streaming applications based on Amazon Nova Sonic 2 and WebRTC with low latency and automatic scaling.
Pulse AI and Amazon Bedrock for automating financial document processing
Pulse AI and Amazon Bedrock help companies extract data from complex financial documents with enterprise-grade accuracy, using a pipeline for extraction and model fine-tuning.
Secure browser for AI agents: how AWS Bedrock uses Chrome policies
AWS Bedrock now supports Chrome security policies, allowing companies to restrict browser-based AI agents to specific domains and sites — an important step for enterprise security.
Stream Vision Agents with Amazon Nova 2 Sonic: voice bots for production in minutes
Stream and Amazon have combined Vision Agents with Nova 2 Sonic to create production-ready voice agents in just minutes without complex infrastructure.
How to improve Amazon Lex bot accuracy with Assisted NLU
AWS has introduced Assisted NLU for Amazon Lex, a tool that improves the accuracy of user intent recognition in chatbots. We explain how to implement it and validate the results.
AWS and Atos showed how gamification speeds up AI training for hundreds of employees
Atos, together with AWS, ran a two-week AI League for 409 participants and showed that gamified fine-tuning competitions build practical skills faster than traditional courses.
How to migrate from Amazon Nova 1 to Nova 2 in Bedrock: model mapping and new capabilities
AWS has published a complete guide to migrating from Amazon Nova 1 to Nova 2: model mapping, API changes, code examples, and a migration checklist.
AWS showed how to build an offline feature store in SageMaker Unified Studio and Catalog
AWS showed how to build an offline feature store in SageMaker Unified Studio: teams publish versioned feature tables to Catalog, while others can safely discover and reuse them.
AWS describes V-RAG — an approach to AI video generation grounded in an image database
AWS describes V-RAG — a setup in which a video model receives not only text, but also images retrieved from a database, to make videos more accurate, cheaper, and more predictable.
Reco reduced incident response time by 63% with Amazon Bedrock
Reco integrated Amazon Bedrock into SaaS security alert handling: the system turns raw JSON into clear summaries, speeding up investigations by 54% and incident response by 63%.
AWS showed how to connect Amazon Bedrock AgentCore to Slack via CDK and Lambda
AWS published a step-by-step integration blueprint for Amazon Bedrock AgentCore with Slack: CDK-based infrastructure, three Lambda functions, SQS, and conversation memory for agentic scenarios.