AWS Machine Learning Blog
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
AWS explained how to deploy Pipecat voice AI agents in Bedrock AgentCore Runtime
AWS released the first part of a guide to deploying Pipecat voice agents in Bedrock AgentCore Runtime and compared WebSockets, WebRTC, TURN, and telephony for production.
AWS showed how Amazon Bedrock analyzes video in three modes and calculates cost
AWS introduced an open video analysis framework for Amazon Bedrock: the service offers three approaches — frame-by-frame, by shots, and via embeddings — with different trade-offs in accuracy, speed, and price.
Ring moved support for 10 regions to Amazon Bedrock Knowledge Bases and cut costs
Ring showed how it built a unified RAG chatbot on Amazon Bedrock Knowledge Bases for 10 international regions, preserved local answer accuracy, and reduced scaling costs by 21%.
AWS opens access to frontier agents for pentesting and DevOps operations in the cloud
AWS has made two frontier agents generally available: Security Agent for on-demand pentesting and DevOps Agent for cloud incidents, promising hours instead of weeks and 3–5x faster response.
AWS showed how to restrict AgentCore AI agents' access to approved domains only
AWS explained how to use AWS Network Firewall to limit internet access for AgentCore resources to a list of allowed domains and use SNI inspection as a basic layer of protection for AI agents.
AWS added persistent session storage and shell command execution to Bedrock AgentCore
AWS showed how to preserve an agent's working directory between sessions in Bedrock AgentCore and run shell commands in the same microVM, so tests, builds, and git operations do not have to go through an LLM.
AWS introduces ActorSimulator for testing multi-turn AI agents in Strands Evals
AWS added ActorSimulator to Strands Evals: it models realistic users and helps test AI agents in multi-turn dialogues with goals, personas, and step tracing.
AWS showed how to connect OAuth-protected MCP servers to Bedrock AgentCore Gateway
AWS explained how to connect OAuth-protected MCP servers through Bedrock AgentCore Gateway so agents can work with enterprise tools through a single controlled entry point.
AWS demonstrates Text-to-SQL on Amazon Bedrock for translating business questions into SQL
AWS described the Text-to-SQL architecture on Amazon Bedrock: the system understands a question in natural language, selects the business context, writes SQL, and returns a final answer.
AWS showed how to embed an AI agent's live view in React via Bedrock AgentCore
AWS released a step-by-step guide and demo app that embeds a live stream of an AI agent's browser into React, so the user can see every click, search, and data entry.
AWS launches Agent Registry in preview - a catalog of AI agents and tools for companies
AWS has opened a preview of Agent Registry as part of AgentCore: the service brings AI agents, tools, and skills together in one place so companies can search, approve, and reuse them without duplication.
AWS Shows How to Build a Virtual Fitting Room for Retail on Nova Canvas
AWS published a ready-made architecture for online retail: virtual try-on, recommendations, and natural language search powered by Nova Canvas, Rekognition, Titan, and OpenSearch.
AWS showed how to cut text-to-SQL costs for business with Amazon Nova Micro and Bedrock
AWS outlined two ways to fine-tune Amazon Nova Micro for custom SQL generation and showed that serverless inference via Bedrock can cost about $0.80 a month for 22,000 requests.
AWS makes new Spring AI SDK for Amazon Bedrock AgentCore generally available
AWS has made the Spring AI SDK for Amazon Bedrock AgentCore generally available: it helps build AI agents on Spring AI with streaming, memory, and tools in a scalable runtime.
Rede Mater Dei deployed 12 AI agents on Amazon Bedrock AgentCore and achieved 517% ROI
Brazilian hospital network Rede Mater Dei uses Amazon Bedrock AgentCore to monitor 12 AI agents and reports 517% ROI, a 66% cut in authorization time, and faster operations.
AWS showed semantic video search on Amazon Bedrock with Nova Multimodal Embeddings
AWS published a reference architecture for video search on Amazon Bedrock: the service splits videos into scenes, separately indexes image, audio, and speech, and combines everything with metadata.
Amazon Bedrock gets detailed inference cost attribution across users and applications
AWS has added detailed cost attribution to Amazon Bedrock: companies can now see exactly who is spending the inference budget across users, roles, services, and tenants.
AWS cut marketing page production from hours to minutes with agentic AI
AWS and Gradial deployed agentic AI on Amazon Bedrock: building and checking marketing web pages now takes about 10 minutes instead of four hours.
AWS makes multimodal BioFMs available for drug development and clinical medicine
Amazon Web Services described how multimodal biological AI models accelerate the search for new drugs, patient stratification in trials, and treatment personalization.
Amazon Quick for marketing: a personal knowledge graph from disparate data
Amazon Quick connects to a marketer’s tools and data, builds a personal knowledge graph, and turns chaos across different systems into strategic decisions.
AWS showed how to fine-tune NVIDIA Nemotron Speech for accurate ASR in niche scenarios
AWS outlined an end-to-end approach to fine-tuning the NVIDIA Nemotron speech model on Amazon EC2: with synthetic audio data, ASR can be adapted more precisely to medicine, support, and other narrow domains.
Amazon demonstrated natural-language search across large video archives with Nova
AWS described the architecture of scalable multimodal video search: Nova generates audio and image embeddings, OpenSearch indexes them, and queries run in milliseconds.
Amazon Bedrock AgentCore gets Policy for AI agent access control
Amazon explained how the new Policy layer in Bedrock AgentCore checks every agent request to tools and data against Cedar rules, without relying on the model's own logic.
AWS explained how to fine-tune Amazon Nova through an LLM judge for complex enterprise tasks
AWS showed a reinforcement fine-tuning setup for Amazon Nova in which a separate LLM evaluates the model's responses, and in a contract review use case Nova 2 Lite outperformed larger solutions.
AWS and vLLM integrated P-EAGLE to speed up large LLM inference by up to 1.69x
AWS showed how P-EAGLE in vLLM removes the bottleneck in speculative decoding, generates multiple tokens in a single pass, and delivers up to a 1.69x speedup.
AWS showed how to build an AI engine for A/B tests on Amazon Bedrock and DynamoDB
AWS published an architecture for an AI system for A/B tests: Bedrock analyzes user context and helps assign variants not randomly, but considering user behavior and experiment conditions.
AWS Shows How to Fine-Tune Amazon Nova via Nova Forge SDK and SageMaker Jobs
AWS released a detailed guide on Nova Forge SDK: from baseline evaluation of Amazon Nova to SFT, RFT, and deployment in SageMaker, raising exact match from 13% to 78.8% and quasi-EM to 80.6%.
AWS launches Nova Forge SDK for fine-tuning Nova models in enterprise AI
AWS has introduced Nova Forge SDK, a toolkit that simplifies customization of Nova models for enterprise teams and removes part of the infrastructure routine.
AWS showed how Amazon Bedrock AgentCore Gateway connects to private APIs and services
AWS showed how Bedrock AgentCore Gateway, via Resource Gateway, gives AI agents access to private APIs and services inside a VPC in managed and self-managed modes.
Amazon unveiled an agentic analytics architecture based on SageMaker, Athena, and Quick
AWS described an architecture in which Amazon Quick, with agentic AI on top of SageMaker, Athena, and S3, lets business users ask questions of a lakehouse in natural language.