Latest publications
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.
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.