Today at NVIDIA GTC 2026, AWS and NVIDIA announced an expanded collaboration with new technology integrations to support growing AI compute demand and help you build and run AI solutions that are production-ready.
This is Part II of a two-part series from the AWS Generative AI Innovation Center. In Part II, we speak directly to the leaders who must turn that shared foundation into action. Each role carries a distinct set of responsibilities, risks, and leverage points. Whether you own a P&L, run enterprise architecture, lead security, govern data, or manage compliance, this section is written in the language of your job—because that's where agentic AI either succeeds or quietly dies.
In this blog post, we introduce the concepts behind next-generation inference capabilities, including disaggregated serving, intelligent request scheduling, and expert parallelism. We discuss their benefits and walk through how you can implement them on Amazon SageMaker HyperPod EKS to achieve significant improvements in inference performance, resource utilization, and operational efficiency.
This blog post provides step-by-step guidance on implementing an offline feature store using SageMaker Catalog within a SageMaker Unified Studio domain. By adopting a publish-subscribe pattern, data producers can use this solution to publish curated, versioned feature tables—while data consumers can securely discover, subscribe to, and reuse them for model development.
In this post, we explain how P-EAGLE works, how we integrated it into vLLM starting from v0.16.0 (PR#32887), and how to serve it with our pre-trained checkpoints.
Today, we’re announcing two new Amazon CloudWatch metrics for Amazon Bedrock, TimeToFirstToken and EstimatedTPMQuotaUsage. In this post, we cover how these work and how to set alarms, establish baselines, and proactively manage capacity using them.
In this post, you will understand how Policy in Amazon Bedrock AgentCore creates a deterministic enforcement layer that operates independently of the agent's own reasoning. You will learn how to turn natural language descriptions of your business rules into Cedar policies, then use those policies to enforce fine-grained, identity-aware controls so that agents only access the tools and data that their users are authorized to use. You will also see how to apply Policy through AgentCore Gateway, intercepting and evaluating every agent-to-tool request at runtime.
This post shows you how to build a scalable multimodal video search system that enables natural language search across large video datasets using Amazon Nova models and Amazon OpenSearch Service. You will learn how to move beyond manual tagging and keyword-based searches to enable semantic search that captures the full richness of video content.
In this post, we explore how to fine-tune a leaderboard-topping, NVIDIA Nemotron Speech Automatic Speech Recognition (ASR) model; Parakeet TDT 0.6B V2. Using synthetic speech data to achieve superior transcription results for specialised applications, we'll walk through an end-to-end workflow that combines AWS infrastructure with the following popular open-source frameworks.
The AWS Generative AI Innovation Center has helped 1,000+ customers move AI into production, delivering millions in documented productivity gains. In this post, we share guidance for leaders across the C-suite: CTOs, CISOs, CDOs, and Chief Data Science/AI officers, as well as business owners and compliance leads.
In this post, we show how to fine-tune a Llama model using Oumi on Amazon EC2 (with the option to create synthetic data using Oumi), store artifacts in Amazon S3, and deploy to Amazon Bedrock using Custom Model Import for managed inference.
We are excited to announce that NVIDIA’s Nemotron 3 Nano is now available as a fully managed and serverless model in Amazon Bedrock. This follows our earlier announcement at AWS re:Invent supporting NVIDIA Nemotron 2 Nano 9B and NVIDIA Nemotron 2 Nano VL 12B models. This post explores the technical characteristics of the NVIDIA Nemotron 3 Nano model and discusses potential application use cases. Additionally, it provides technical guidance to help you get started using this model for your generative AI applications within the Amazon Bedrock environment.
In this post, you will discover how to use Amazon Bedrock's Global cross-Region Inference for Claude models in India. We will guide you through the capabilities of each Claude model variant and how to get started with a code example to help you start building generative AI applications immediately.
In this post, we walk through a multi-developer CI/CD pipeline for Amazon Lex that enables isolated development environments, automated testing, and streamlined deployments. We show you how to set up the solution and share real-world results from teams using this approach.
This post demonstrates how to build custom model parsers for Strands agents when working with LLMs hosted on SageMaker that don't natively support the Bedrock Messages API format. We'll walk through deploying Llama 3.1 with SGLang on SageMaker using awslabs/ml-container-creator, then implementing a custom parser to integrate it with Strands agents.
Organizations find it challenging to implement a secure embedded chat in their applications and can require weeks of development to build authentication, token validation, domain security, and global distribution infrastructure. In this post, we show you how to solve this with a one-click deployment solution to embed the chat agents using the Quick Suite Embedding SDK in enterprise portals.
In this post, we discuss how Amazon Nova demonstrates capabilities in conversational analytics, call classification, and other use cases often relevant to contact center solutions. We examine these capabilities for both single-call and multi-call analytics use cases.
This post explores how Ricoh built a standardized, multi-tenant solution for automated document classification and extraction using the AWS GenAI IDP Accelerator as a foundation, transforming their document processing from a custom-engineering bottleneck into a scalable, repeatable service.
In this post, we explore the virtual try-on capability now available in Amazon Nova Canvas, including sample code to get started quickly and tips to help get the best outputs.
This post details how Lendi Group built their AI-powered Home Loan Guardian using Amazon Bedrock, the challenges they faced, the architecture they implemented, and the significant business outcomes they’ve achieved. Their journey offers valuable insights for organizations that want to use generative AI to transform customer experiences while maintaining the human touch that builds trust and loyalty.
In this post, we show you how to connect Quick Suite with Tines to securely retrieve, analyze, and visualize enterprise data from any security or IT system. We walk through an example that uses a MCP server in Tines to retrieve data from various tools, such as AWS CloudTrail, Okta, and VirusTotal, to remediate security events using Quick Suite.
In this post, we share results from the AWS China Applied Science team's comprehensive evaluation of Nova Forge using a challenging Voice of Customer (VOC) classification task, benchmarked against open-source models.
This post explores how to build an intelligent conversational agent using Amazon Bedrock, LangGraph, and managed MLflow on Amazon SageMaker AI.
In this post, we will show you how to configure Amazon Bedrock Guardrails for efficient performance, implement best practices to protect your applications, and monitor your deployment effectively to maintain the right balance between safety and user experience.
Delivering successful COBOL modernization requires a solution that can reverse engineer deterministically, produce validated and traceable specs, and help those specs flow into any AI-powered coding assistant for the forward engineering. A successful modernization requires both reverse engineering and forward engineering. Learn more about COBOL in this post.
In this post, we explore reinforcement fine-tuning (RFT) for Amazon Nova models, which can be a powerful customization technique that learns through evaluation rather than imitation. We'll cover how RFT works, when to use it versus supervised fine-tuning, real-world applications from code generation to customer service, and implementation options ranging from fully managed Amazon Bedrock to multi-turn agentic workflows with Nova Forge. You'll also learn practical guidance on data preparation, reward function design, and best practices for achieving optimal results.
AWS recently released significant updates to the Large Model Inference (LMI) container, delivering comprehensive performance improvements, expanded model support, and streamlined deployment capabilities for customers hosting LLMs on AWS. These releases focus on reducing operational complexity while delivering measurable performance gains across popular model architectures.
In this post, we explain how we implemented multi-LoRA inference for Mixture of Experts (MoE) models in vLLM, describe the kernel-level optimizations we performed, and show you how you can benefit from this work. We use GPT-OSS 20B as our primary example throughout this post.
This post demonstrates how to quickly deploy a production-ready event assistant using the components of Amazon Bedrock AgentCore. We'll build an intelligent companion that remembers attendee preferences and builds personalized experiences over time, while Amazon Bedrock AgentCore handles the heavy lifting of production deployment: Amazon Bedrock AgentCore Memory for maintaining both conversation context and long-term preferences without custom storage solutions, Amazon Bedrock AgentCore Identity for secure multi-IDP authentication, and Amazon Bedrock AgentCore Runtime for serverless scaling and session isolation. We will also use Amazon Bedrock Knowledge Bases for managed RAG and event data retrieval.
In this post, we show you how to build a comprehensive photo search system using the AWS Cloud Development Kit (AWS CDK) that integrates Amazon Rekognition for face and object detection, Amazon Neptune for relationship mapping, and Amazon Bedrock for AI-powered captioning.
In this post, we demonstrate how to train CodeFu-7B, a specialized 7-billion parameter model for competitive programming, using Group Relative Policy Optimization (GRPO) with veRL, a flexible and efficient training library for large language models (LLMs) that enables straightforward extension of diverse RL algorithms and seamless integration with existing LLM infrastructure, within a distributed Ray cluster managed by SageMaker training jobs. We walk through the complete implementation, covering data preparation, distributed training setup, and comprehensive observability, showcasing how this unified approach delivers both computational scale and developer experience for sophisticated RL training workloads.
This post explores the implementation of Dottxt’s Outlines framework as a practical approach to implementing structured outputs using AWS Marketplace in Amazon SageMaker.
In this post, we are exciting to announce availability of Global CRIS for customers in Thailand, Malaysia, Singapore, Indonesia, and Taiwan and give a walkthrough of technical implementation steps, and cover quota management best practices to maximize the value of your AI Inference deployments. We also provide guidance on best practices for production deployments.
We’re excited to announce the availability of Anthropic’s Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, and Claude Haiku 4.5 through Amazon Bedrock global cross-Region inference for customers operating in the Middle East. In this post, we guide you through the capabilities of each Anthropic Claude model variant, the key advantages of global cross-Region inference including improved resilience, real-world use cases you can implement, and a code example to help you start building generative AI applications immediately.
In this post, we examine how Bedrock Robotics tackles this challenge. By joining the AWS Physical AI Fellowship, the startup partnered with the AWS Generative AI Innovation Center to apply vision-language models that analyze construction video footage, extract operational details, and generate labeled training datasets at scale, to improve data preparation for autonomous construction equipment.
In this post, we explore how Sonrai, a life sciences AI company, partnered with AWS to build a robust MLOps framework using Amazon SageMaker AI that addresses these challenges while maintaining the traceability and reproducibility required in regulated environments.
In this blog post, we demonstrate how Hexagon collaborated with Amazon Web Services to scale their AI model production by pretraining state-of-the-art segmentation models, using the model training infrastructure of Amazon SageMaker HyperPod.
Hugging Face smolagents is an open source Python library designed to make it straightforward to build and run agents using a few lines of code. We will show you how to build an agentic AI solution by integrating Hugging Face smolagents with Amazon Web Services (AWS) managed services. You'll learn how to deploy a healthcare AI agent that demonstrates multi-model deployment options, vector-enhanced knowledge retrieval, and clinical decision support capabilities.
In 2025, Amazon SageMaker AI saw dramatic improvements to core infrastructure offerings along four dimensions: capacity, price performance, observability, and usability. In this series of posts, we discuss these various improvements and their benefits. In Part 1, we discuss capacity improvements with the launch of Flexible Training Plans. We also describe improvements to price performance for inference workloads. In Part 2, we discuss enhancements made to observability, model customization, and model hosting.
In 2025, Amazon SageMaker AI made several improvements designed to help you train, tune, and host generative AI workloads. In Part 1 of this series, we discussed Flexible Training Plans and price performance improvements made to inference components. In this post, we discuss enhancements made to observability, model customization, and model hosting. These improvements facilitate a whole new class of customer use cases to be hosted on SageMaker AI.
In this post, you’ll use a six-step checklist to build a new MCP server or validate and adjust an existing MCP server for Amazon Quick integration. The Amazon Quick User Guide describes the MCP client behavior and constraints. This is a “How to” guide for detailed implementation required by 3P partners to integrate with Amazon Quick with MCP.
In this post, we explain how you can use the Flyte Python SDK to orchestrate and scale AI/ML workflows. We explore how the Union.ai 2.0 system enables deployment of Flyte on Amazon Elastic Kubernetes Service (Amazon EKS), integrating seamlessly with AWS services like Amazon Simple Storage Service (Amazon S3), Amazon Aurora, AWS Identity and Access Management (IAM), and Amazon CloudWatch. We explore the solution through an AI workflow example, using the new Amazon S3 Vectors service.
In this blog post, we will guide you through establishing data source connectivity between Amazon Quick Sight and Snowflake through secure key pair authentication.
In this post, we demonstrate how to build unified intelligence systems using Amazon Bedrock AgentCore through our real-world implementation of the Customer Agent and Knowledge Engine (CAKE).
In this post, we present a comprehensive evaluation framework for Amazon agentic AI systems that addresses the complexity of agentic AI applications at Amazon through two core components: a generic evaluation workflow that standardizes assessment procedures across diverse agent implementations, and an agent evaluation library that provides systematic measurements and metrics in Amazon Bedrock AgentCore Evaluations, along with Amazon use case-specific evaluation approaches and metrics.
The release of Anthropic Claude Sonnet 4.5 in the AWS GovCloud (US) Region introduces a straightforward on-ramp for AI-assisted development for workloads with regulatory compliance requirements. In this post, we explore how to combine Claude Sonnet 4.5 on Amazon Bedrock in AWS GovCloud (US) with Claude Code, an agentic coding assistant released by Anthropic. This […]
Today, we are announcing three new capabilities that address these requirements: proxy configuration, browser profiles, and browser extensions. Together, these features give you fine-grained control over how your AI agents interact with the web. This post will walk through each capability with configuration examples and practical use cases to help you get started.
In this post, we show how to create an AI-powered recruitment system using Amazon Bedrock, Amazon Bedrock Knowledge Bases, AWS Lambda, and other AWS services to enhance job description creation, candidate communication, and interview preparation while maintaining human oversight.
In this post, we provide you with a comprehensive approach to achieve this. First, we introduce a context message strategy that maintains continuous communication between servers and clients during extended operations. Next, we develop an asynchronous task management framework that allows your AI agents to initiate long-running processes without blocking other operations. Finally, we demonstrate how to bring these strategies together with Amazon Bedrock AgentCore and Strands Agents to build production-ready AI agents that can handle complex, time-intensive operations reliably.
Today we’re excited to announce that the NVIDIA Nemotron 3 Nano 30B model with 3B active parameters is now generally available in the Amazon SageMaker JumpStart model catalog. You can accelerate innovation and deliver tangible business value with Nemotron 3 Nano on Amazon Web Services (AWS) without having to manage model deployment complexities. You can power your generative AI applications with Nemotron capabilities using the managed deployment capabilities offered by SageMaker JumpStart.
This post shows you how to implement robust error handling strategies that can help improve application reliability and user experience when using Amazon Bedrock. We'll dive deep into strategies for optimizing performances for the application with these errors. Whether this is for a fairly new application or matured AI application, in this post you will be able to find the practical guidelines to operate with on these errors.
This post shows you how to implement intelligent notification filtering using Amazon Bedrock and its gen-AI capabilities. You'll learn model selection strategies, cost optimization techniques, and architectural patterns for deploying gen-AI at IoT scale, based on Swann Communications deployment across millions of devices.
LinqAlpha is a Boston-based multi-agent AI system built specifically for institutional investors. The system supports and streamlines agentic workflows across company screening, primer generation, stock price catalyst mapping, and now, pressure-testing investment ideas through a new AI agent called Devil’s Advocate. In this post, we share how LinqAlpha uses Amazon Bedrock to build and scale Devil’s Advocate.
In this post, we discuss how Amazon Nova in Amazon Bedrock can be used to implement an AI-powered image recognition solution that automates the detection and validation of module components, significantly reducing manual verification efforts and improving accuracy.
Iberdrola, one of the world’s largest utility companies, has embraced cutting-edge AI technology to revolutionize its IT operations in ServiceNow. Through its partnership with AWS, Iberdrola implemented different agentic architectures using Amazon Bedrock AgentCore, targeting three key areas: optimizing change request validation in the draft phase, enriching incident management with contextual intelligence, and simplifying change model selection using conversational AI. These innovations reduce bottlenecks, help teams accelerate ticket resolution, and deliver consistent and high-quality data handling throughout the organization.
Amazon Nova Sonic delivers real-time, human-like voice conversations through the bidirectional streaming interface. In this post, you learn how Amazon Nova Sonic can solve some of the challenges faced by cascaded approaches, simplify building voice AI agents, and provide natural conversational capabilities. We also provide guidance on when to choose each approach to help you make informed decisions for your voice AI projects.
This blog post dives deeper into the implementation architecture for the Automated Reasoning checks rewriting chatbot.
In this post, we show how this integrated approach transforms enterprise LLM fine-tuning from a complex, resource-intensive challenge into a streamlined, scalable solution for achieving better model performance in domain-specific applications.
Working with the Generative AI Innovation Center, New Relic NOVA (New Relic Omnipresence Virtual Assistant) evolved from a knowledge assistant into a comprehensive productivity engine. We explore the technical architecture, development journey, and key lessons learned in building an enterprise-grade AI solution that delivers measurable productivity gains at scale.
In this post, you will learn how to deploy Fullstack AgentCore Solution Template (FAST) to your Amazon Web Services (AWS) account, understand its architecture, and see how to extend it for your requirements. You will learn how to build your own agent while FAST handles authentication, infrastructure as code (IaC), deployment pipelines, and service integration.
This post walks through how agent-to-agent collaboration on Amazon Bedrock works in practice, using Amazon Nova 2 Lite for planning and Amazon Nova Act for browser interaction, to turn a fragile single-agent setup into a predictable multi-agent system.
Today, we're announcing structured outputs on Amazon Bedrock—a capability that fundamentally transforms how you can obtain validated JSON responses from foundation models through constrained decoding for schema compliance. In this post, we explore the challenges of traditional JSON generation and how structured outputs solves them. We cover the two core mechanisms—JSON Schema output format and strict tool use—along with implementation details, best practices, and practical code examples.
In this post, we demonstrate how to use the CLI and the SDK to create and manage SageMaker HyperPod clusters in your AWS account. We walk through a practical example and dive deeper into the user workflow and parameter choices.
In this post, we explore the Amazon Nova rubric-based judge feature: what a rubric-based judge is, how the judge is trained, what metrics to consider, and how to calibrate the judge. We chare notebook code of the Amazon Nova rubric-based LLM-as-a-judge methodology to evaluate and compare the outputs of two different LLMs using SageMaker training jobs.
Associa collaborated with the AWS Generative AI Innovation Center to build a generative AI-powered document classification system aligning with Associa’s long-term vision of using generative AI to achieve operational efficiencies in document management. The solution automatically categorizes incoming documents with high accuracy, processes documents efficiently, and provides substantial cost savings while maintaining operational excellence. The document classification system, developed using the Generative AI Intelligent Document Processing (GenAI IDP) Accelerator, is designed to integrate seamlessly into existing workflows. It revolutionizes how employees interact with document management systems by reducing the time spent on manual classification tasks.
In this post, you will learn how to configure and use Amazon Nova Multimodal Embeddings for media asset search systems, product discovery experiences, and document retrieval applications.
Building upon our earlier work of marketing campaign image generation using Amazon Nova foundation models, in this post, we demonstrate how to enhance image generation by learning from previous marketing campaigns. We explore how to integrate Amazon Bedrock, AWS Lambda, and Amazon OpenSearch Serverless to create an advanced image generation system that uses reference campaigns to maintain brand guidelines, deliver consistent content, and enhance the effectiveness and efficiency of new campaign creation.
BGL is a leading provider of self-managed superannuation fund (SMSF) administration solutions that help individuals manage the complex compliance and reporting of their own or a client’s retirement savings, serving over 12,700 businesses across 15 countries. In this blog post, we explore how BGL built its production-ready AI agent using Claude Agent SDK and Amazon Bedrock AgentCore.
In this post, we demonstrate how to build a secure file upload solution by integrating Google Drive with Amazon Quick Suite custom connectors using Amazon API Gateway and AWS Lambda.
This post explores nine essential best practices for building enterprise AI agents using Amazon Bedrock AgentCore. Amazon Bedrock AgentCore is an agentic platform that provides the services you need to create, deploy, and manage AI agents at scale. In this post, we cover everything from initial scoping to organizational scaling, with practical guidance that you can apply immediately.
On November 21, 2025, Amazon SageMaker introduced a built-in data agent within Amazon SageMaker Unified Studio that transforms large-scale data analysis. In this post, we demonstrate, through a detailed case study of an epidemiologist conducting clinical cohort analysis, how SageMaker Data Agent can help reduce weeks of data preparation into days, and days of analysis development into hours—ultimately accelerating the path from clinical questions to research conclusions.
In this post, we illustrate how Clarus Care, a healthcare contact center solutions provider, worked with the AWS Generative AI Innovation Center (GenAIIC) team to develop a generative AI-powered contact center prototype. This solution enables conversational interaction and multi-intent resolution through an automated voicebot and chat interface. It also incorporates a scalable service model to support growth, human transfer capabilities--when requested or for urgent cases--and an analytics pipeline for performance insights.
This post explores how you can use Amazon S3-based templates to simplify ModelOps workflows, walk through the key benefits compared to using Service Catalog approaches, and demonstrates how to create a custom ModelOps solution that integrates with GitHub and GitHub Actions—giving your team one-click provisioning of a fully functional ML environment.
In this post, we walk through how global cross-Region inference routes requests and where your data resides, then show you how to configure the required AWS Identity and Access Management (IAM) permissions and invoke Claude 4.5 models using the global inference profile Amazon Resource Name (ARN). We also cover how to request quota increases for your workload. By the end, you'll have a working implementation of global cross-Region inference in af-south-1.
The agent-based approach we present is applicable to any type of enterprise content, from product documentation and knowledge bases to marketing materials and technical specifications. To demonstrate these concepts in action, we walk through a practical example of reviewing blog content for technical accuracy. These patterns and techniques can be directly adapted to various content review needs by adjusting the agent configurations, tools, and verification sources.
In this post, we walk you through Pushpay's journey in building this solution and explore how Pushpay used Amazon Bedrock to create a custom generative AI evaluation framework for continuous quality assurance and establishing rapid iteration feedback loops on AWS.
This blog post demonstrates how to build an intelligent contract management solution using Amazon Quick Suite as your primary contract management solution, augmented with Amazon Bedrock AgentCore for advanced multi-agent capabilities.
In this post, we discuss how to use AppSync Events as the foundation of a capable, serverless, AI gateway architecture. We explore how it integrates with AWS services for comprehensive coverage of the capabilities offered in AI gateway architectures. Finally, we get you started on your journey with sample code you can launch in your account and begin building.
This blog post describes how Totogi automates change request processing by partnering with the AWS Generative AI Innovation Center and using the rapid innovation capabilities of Amazon Bedrock.
Amazon Bedrock AgentCore services are now being supported by various IaC frameworks such as AWS Cloud Development Kit (AWS CDK), Terraform and AWS CloudFormation Templates. This integration brings the power of IaC directly to AgentCore so developers can provision, configure, and manage their AI agent infrastructure. In this post, we use CloudFormation templates to build an end-to-end application for a weather activity planner.
In this post, we demonstrate how the Amazon Catalog Team built a self-learning system that continuously improves accuracy while reducing costs at scale using Amazon Bedrock.
PDI Technologies is a global leader in the convenience retail and petroleum wholesale industries. In this post, we walk through the PDI Intelligence Query (PDIQ) process flow and architecture, focusing on the implementation details and the business outcomes it has helped PDI achieve.
In this post, we demonstrate how CLICKFORCE used AWS services to build Lumos and transform advertising industry analysis from weeks-long manual work into an automated, one-hour process.
This blog post explains how TR's Platform Engineering team, a geographically distributed unit overseeing TR's service availability, boosted its operational productivity by transitioning from manual to an automated agentic system using Amazon Bedrock AgentCore.
In this post, we walk you through the complete architecture to structure and store episodes, discuss the reflection module, and share compelling benchmarks that demonstrate significant improvements in agent task success rates.
In this post, we show how bunq upgraded Finn, its in-house generative AI assistant, using Amazon Bedrock to transform user support and banking operations to be seamless, in multiple languages and time zones.
In this post, we explore how to build a multi-agent video processing workflow using Strands Agents, Meta's Llama 4 models, and Amazon Bedrock to automatically analyze and understand video content through specialized AI agents working in coordination. To showcase the solution, we will use Amazon SageMaker AI to walk you through the code.
In this post, we'll guide you through building multimodal RAG applications. You'll learn how multimodal knowledge bases work, how to choose the right processing strategy based on your content type, and how to configure and implement multimodal retrieval using both the console and code examples.
In this post, we show you how fine-tuning enabled a 33% reduction in dangerous medication errors (Amazon Pharmacy), engineering 80% human effort reduction (Amazon Global Engineering Services), and content quality assessments improving 77% to 96% accuracy (Amazon A+). This post details the techniques behind these outcomes: from foundational methods like Supervised Fine-Tuning (SFT) (instruction tuning), and Proximal Policy Optimization (PPO), to Direct Preference Optimization (DPO) for human alignment, to cutting-edge reasoning optimizations such as Grouped-based Reinforcement Learning from Policy Optimization (GRPO), Direct Advantage Policy Optimization (DAPO), and Group Sequence Policy Optimization (GSPO) purpose-built for agentic systems.
The AWS AI League, launched by Amazon Web Services (AWS), expanded its reach to the Association of Southeast Asian Nations (ASEAN) last year, welcoming student participants from Singapore, Indonesia, Malaysia, Thailand, Vietnam, and the Philippines. In this blog post, you’ll hear directly from the AWS AI League champion, Blix D. Foryasen, as he shares his reflection on the challenges, breakthroughs, and key lessons discovered throughout the competition.
In this post, we demonstrate how to use a GitHub Actions workflow to automate the deployment of AI agents on AgentCore Runtime. This approach delivers a scalable solution with enterprise-level security controls, providing complete continuous integration and delivery (CI/CD) automation.
In this post, we explain how we overcame the limitations of single-agent AI systems through a human-centric approach, implemented structured outputs to significantly reduce hallucinations and built a scalable solution now positioned for expansion across the AMET QA team and later across other QA teams in International Emerging Stores and Payments (IESP) Org.
This post introduces generative AI guided business reporting—with a focus on writing achievements & challenges about your business—providing a smart, practical solution that helps simplify and accelerate internal communication and reporting.
In this post, we demonstrate how you can address these challenges by adding centralized safeguards to a custom multi-provider generative AI gateway using Amazon Bedrock Guardrails.
In this post, we describe how you can use Amazon Nova Multimodal Embeddings to retrieve specific video segments. We also review a real-world use case in which Nova Multimodal Embeddings achieved a recall success rate of 96.7% and a high-precision recall of 73.3% (returning the target content in the top two results) when tested against a library of 170 gaming creative assets. The model also demonstrates strong cross-language capabilities with minimal performance degradation across multiple languages.
In this post, we explore the architecture that AutoScout24 used to build their standardized AI development framework, enabling rapid deployment of secure and scalable AI agents.
This post explores how new serverless model customization capabilities, elastic training, checkpointless training, and serverless MLflow work together to accelerate your AI development from months to days.
In this post, we explore the security considerations and best practices for implementing Amazon Bedrock cross-Region inference profiles. Whether you're building a generative AI application or need to meet specific regional compliance requirements, this guide will help you understand the secure architecture of Amazon Bedrock CRIS and how to properly configure your implementation.
This post is co-written with Sunaina Kavi, AI/ML Product Manager at Omada Health. Omada Health, a longtime innovator in virtual healthcare delivery, launched a new nutrition experience in 2025, featuring OmadaSpark, an AI agent trained with robust clinical input that delivers real-time motivational interviewing and nutrition education. It was built on AWS. OmadaSpark was designed […]
In this post, we explore how Amazon Nova Multimodal Embeddings addresses the challenges of crossmodal search through a practical ecommerce use case. We examine the technical limitations of traditional approaches and demonstrate how Amazon Nova Multimodal Embeddings enables retrieval across text, images, and other modalities. You learn how to implement a crossmodal search system by generating embeddings, handling queries, and measuring performance. We provide working code examples and share how to add these capabilities to your applications.
Quantized models can be seamlessly deployed on Amazon SageMaker AI using a few lines of code. In this post, we explore why quantization matters—how it enables lower-cost inference, supports deployment on resource-constrained hardware, and reduces both the financial and environmental impact of modern LLMs, while preserving most of their original performance. We also take a deep dive into the principles behind PTQ and demonstrate how to quantize the model of your choice and deploy it on Amazon SageMaker.
Beekeeper’s automated leaderboard approach and human feedback loop system for dynamic LLM and prompt pair selection addresses the key challenges organizations face in navigating the rapidly evolving landscape of language models.
This post, developed through a strategic scientific partnership between AWS and the Instituto de Ciência e Tecnologia Itaú (ICTi), P&D hub maintained by Itaú Unibanco, the largest private bank in Latin America, explores the technical aspects of sentiment analysis for both text and audio. We present experiments comparing multiple machine learning (ML) models and services, discuss the trade-offs and pitfalls of each approach, and highlight how AWS services can be orchestrated to build robust, end-to-end solutions. We also offer insights into potential future directions, including more advanced prompt engineering for large language models (LLMs) and expanding the scope of audio-based analysis to capture emotional cues that text data alone might miss.
This post provides a detailed architectural overview of how TrueLook built its AI-powered safety monitoring system using SageMaker AI, highlighting key technical decisions, pipeline design patterns, and MLOps best practices. You will gain valuable insights into designing scalable computer vision solutions on AWS, particularly around model training workflows, automated pipeline creation, and production deployment strategies for real-time inference.
This two-part series explores Flo Health's journey with generative AI for medical content verification. Part 1 examines our proof of concept (PoC), including the initial solution, capabilities, and early results. Part 2 covers focusing on scaling challenges and real-world implementation. Each article stands alone while collectively showing how AI transforms medical content management at scale.
This post shows an automated PII detection and redaction solution using Amazon Bedrock Data Automation and Amazon Bedrock Guardrails through a use case of processing text and image content in high volumes of incoming emails and attachments. The solution features a complete email processing workflow with a React-based user interface for authorized personnel to more securely manage and review redacted email communications and attachments. We walk through the step-by-step solution implementation procedures used to deploy this solution. Finally, we discuss the solution benefits, including operational efficiency, scalability, security and compliance, and adaptability.
Observe.ai developed the One Load Audit Framework (OLAF), which integrates with SageMaker to identify bottlenecks and performance issues in ML services, offering latency and throughput measurements under both static and dynamic data loads. In this blog post, you will learn how to use the OLAF utility to test and validate your SageMaker endpoint.
This post shows you how to migrate your self-managed MLflow tracking server to a MLflow App – a serverless tracking server on SageMaker AI that automatically scales resources based on demand while removing server patching and storage management tasks at no cost. Learn how to use the MLflow Export Import tool to transfer your experiments, runs, models, and other MLflow resources, including instructions to validate your migration's success.
This post demonstrates how to solve this challenge by building an AI-powered website assistant using Amazon Bedrock and Amazon Bedrock Knowledge Bases.
In this post, we explore how to programmatically create an IDP solution that uses Strands SDK, Amazon Bedrock AgentCore, Amazon Bedrock Knowledge Base, and Bedrock Data Automation (BDA). This solution is provided through a Jupyter notebook that enables users to upload multi-modal business documents and extract insights using BDA as a parser to retrieve relevant chunks and augment a prompt to a foundational model (FM).
Enterprise organizations increasingly rely on web-based applications for critical business processes, yet many workflows remain manually intensive, creating operational inefficiencies and compliance risks. Despite significant technology investments, knowledge workers routinely navigate between eight to twelve different web applications during standard workflows, constantly switching contexts and manually transferring information between systems. Data entry and validation tasks […]
In this post, we explore how agentic QA automation addresses these challenges and walk through a practical example using Amazon Bedrock AgentCore Browser and Amazon Nova Act to automate testing for a sample retail application.
In this post, we demonstrate how to optimize large language model (LLM) inference on Amazon SageMaker AI using BentoML's LLM-Optimizer to systematically identify the best serving configurations for your workload.
In this post, we explore how Mantle, Amazon's next-generation inference engine for Amazon Bedrock, implements a zero operator access (ZOA) design that eliminates any technical means for AWS operators to access customer data.
In this post, we explore the new AWS AI League challenges and how they are transforming how organizations approach AI development. The grand finale at AWS re:Invent 2025 was an exciting showcase of their ingenuity and skills.
In this post, we demonstrate how to use Foundation Models (FMs) from Amazon Bedrock and the newly launched Amazon Bedrock AgentCore alongside W&B Weave to help build, evaluate, and monitor enterprise AI solutions. We cover the complete development lifecycle from tracking individual FM calls to monitoring complex agent workflows in production.
In this post, we explore how Qbtech streamlined their machine learning (ML) workflow using Amazon SageMaker AI, a fully managed service to build, train and deploy ML models, and AWS Glue, a serverless service that makes data integration simpler, faster, and more cost effective. This new solution reduced their feature engineering time from weeks to hours, while maintaining the high clinical standards required by healthcare providers.
In this post, the first of a series of three, we focus on how you can use Amazon Nova to streamline, simplify, and accelerate marketing campaign creation through generative AI. We show how Bancolombia, one of Colombia’s largest banks, is experimenting with the Amazon Nova models to generate visuals for their marketing campaigns.
In this post, we explore how AWS and Visa are partnering to enable agentic commerce through Visa Intelligent Commerce using Amazon Bedrock AgentCore. We demonstrate how autonomous AI agents can transform fragmented shopping and travel experiences into seamless, end-to-end workflows—from discovery and comparison to secure payment authorization—all driven by natural language.
This post explores Chain-of-Draft (CoD), an innovative prompting technique introduced in a Zoom AI Research paper Chain of Draft: Thinking Faster by Writing Less, that revolutionizes how models approach reasoning tasks. While Chain-of-Thought (CoT) prompting has been the go-to method for enhancing model reasoning, CoD offers a more efficient alternative that mirrors human problem-solving patterns—using concise, high-signal thinking steps rather than verbose explanations.
In this post, we demonstrate hosting Voxtral models on Amazon SageMaker AI endpoints using vLLM and the Bring Your Own Container (BYOC) approach. vLLM is a high-performance library for serving large language models (LLMs) that features paged attention for improved memory management and tensor parallelism for distributing models across multiple GPUs.
To address the need for businesses to quickly analyze information and unlock actionable insights, we are announcing Analytics Agent, a new feature that is seamlessly integrated into the GenAI IDP Accelerator. With this feature, users can perform advanced searches and complex analyses using natural language queries without SQL or data analysis expertise. In this post, we discuss how non-technical users can use this tool to analyze and understand the documents they have processed at scale with natural language.
In this post, we demonstrate how to implement a predictive maintenance solution using Foundation Models (FMs) on Amazon Bedrock, with a case study of Amazon's manufacturing equipment within their fulfillment centers. The solution is highly adaptable and can be customized for other industries, including oil and gas, logistics, manufacturing, and healthcare.
Today, we are excited to introduce a new feature for SageMaker Studio: SOCI (Seekable Open Container Initiative) indexing. SOCI supports lazy loading of container images, where only the necessary parts of an image are downloaded initially rather than the entire container.
This post demonstrates how to use the powerful combination of Strands Agents, Amazon Bedrock AgentCore, and NVIDIA NeMo Agent Toolkit to build, evaluate, optimize, and deploy AI agents on Amazon Web Services (AWS) from initial development through production deployment.
In this post, you will learn about bi-directional streaming on AgentCore Runtime and the prerequisites to create a WebSocket implementation. You will also learn how to use Strands Agents to implement a bi-directional streaming solution for voice agents.
In this post, we'll explore the new capabilities and core concepts that help organizations track and manage models development and deployment lifecycles. We will show you how the features are configured to train models with automatic end-to-end lineage, from dataset upload and versioning to model fine-tuning, evaluation, and seamless endpoint deployment.
In this post, we demonstrate how to integrate Amazon SageMaker managed MLflow as a central repository to log these experiments and provide a unified system for monitoring their progress.
Picture this: Your enterprise has just deployed its first generative AI application. The initial results are promising, but as you plan to scale across departments, critical questions emerge. How will you enforce consistent security, prevent model bias, and maintain control as AI applications multiply?
In this post, we explore how Tata Power CoE and Oneture Technologies use AWS services to automate the inspection process end-to-end.
In this post, we'll show how the TwelveLabs Marengo embedding model, available on Amazon Bedrock, enhances video understanding through multimodal AI. We'll build a video semantic search and analysis solution using embeddings from the Marengo model with Amazon OpenSearch Serverless as the vector database, for semantic search capabilities that go beyond simple metadata matching to deliver intelligent content discovery.
In this post, we introduce checkpointless training on Amazon SageMaker HyperPod, a paradigm shift in model training that reduces the need for traditional checkpointing by enabling peer-to-peer state recovery. Results from production-scale validation show 80–93% reduction in recovery time (from 15–30 minutes or more to under 2 minutes) and enables up to 95% training goodput on cluster sizes with thousands of AI accelerators.
Amazon SageMaker HyperPod now supports elastic training, enabling your machine learning (ML) workloads to automatically scale based on resource availability. In this post, we demonstrate how elastic training helps you maximize GPU utilization, reduce costs, and accelerate model development through dynamic resource adaptation, while maintain training quality and minimizing manual intervention.
In this post, we explore two powerful orchestration patterns implemented with Strands Agents. Using a common set of travel planning tools, we demonstrate how different orchestration strategies can solve the same problem through distinct reasoning approaches,
In this first part of our two-part series, you'll learn how to evolve your existing DevOps architecture for generative AI workloads and implement GenAIOps practices. We'll showcase practical implementation strategies for different generative AI adoption levels, focusing on consuming foundation models.
In this post, we present practical techniques and recommendations for optimizing throughput in ML training workloads that read data directly from Amazon S3 general purpose buckets.
In this post, we explore how to build a sophisticated voice-powered AWS operations assistant using Amazon Nova Sonic for speech processing and Strands Agents for multi-agent orchestration. This solution demonstrates how natural language voice interactions can transform cloud operations, making AWS services more accessible and operations more efficient.
This post walks through how Harmonic Security used Amazon SageMaker AI, Amazon Bedrock, and Amazon Nova Pro to fine-tune a ModernBERT model, achieving low-latency, accurate, and scalable data leakage detection.
In this post, we'll show how Swisscom implemented Amazon Bedrock AgentCore to build and scale their enterprise AI agents for customer support and sales operations. As an early adopter of Amazon Bedrock in the AWS Europe Region (Zurich), Swisscom leads in enterprise AI implementation with their Chatbot Builder system and various AI initiatives. Their successful deployments include Conversational AI powered by Rasa and fine-tuned LLMs on Amazon SageMaker, and the Swisscom Swisscom myAI assistant, built to meet Swiss data protection standards.
Today we’re announcing Amazon SageMaker AI with MLflow, now including a serverless capability that dynamically manages infrastructure provisioning, scaling, and operations for artificial intelligence and machine learning (AI/ML) development tasks. In this post, we explore how these new capabilities help you run large MLflow workloads—from generative AI agents to large language model (LLM) experimentation—with improved performance, automation, and security using SageMaker AI with MLflow.
In this post, we explain how to integrate Langfuse observability with Amazon Bedrock AgentCore to gain deep visibility into an AI agent's performance, debug issues faster, and optimize costs. We walk through a complete implementation using Strands agents deployed on AgentCore Runtime followed by step-by-step code examples.
This post evaluates the reasoning capabilities of our latest offering in the Nova family, Amazon Nova Lite 2.0, using practical scenarios that test these critical dimensions. We compare its performance against other models in the Nova family—Lite 1.0, Micro, Pro 1.0, and Premier—to elucidate how the latest version advances reasoning quality and consistency.
In this post, we show how to build chat agents in Amazon Quick Suite. We walk through a three-layer framework—identity, instructions, and knowledge—that transforms Quick Suite chat agents into intelligent enterprise AI assistants. In our example, we demonstrate how our chat agent guides feature discovery, use enterprise data to inform recommendations, and tailors solutions based on potential to impact and your team’s adoption readiness.
Experts at the Generative AI Innovation Center share several strategies to help organizations excel with generative AI.
Today, we are pleased to announce a new integration between Amazon Quick Research and S&P Global. This integration brings both S&P Global Energy news, research, and insights and S&P Global Market Intelligence data to Quick Research customers in one deep research agent. In this post, we explore S&P Global’s data sets and the solution architecture of the integration with Quick Research.
AgentCore Gateway now supports API GatewayAs organizations explore the possibilities of agentic applications, they continue to navigate challenges of using enterprise data as context in invocation requests to large language models (LLMs) in a manner that is secure and aligned with enterprise policies. This post covers these new capabilities and shows how to implement them.
In this post, we demonstrate how to build an intelligent insurance underwriting agent that addresses three critical challenges: unifying siloed data across CRM systems and databases, providing explainable and auditable AI decisions for regulatory compliance, and enabling automated fraud detection with consistent underwriting rules. The solution combines Amazon Nova 2 Lite for transparent risk assessment, Amazon Bedrock AgentCore for managed MCP server infrastructure, and Amazon Quick Suite for natural language interactions—delivering a production-ready system that underwriters can deploy in under 30 minutes .
In this post, we explore how Myriad Genetics partnered with the AWS Generative AI Innovation Center to transform their healthcare document processing pipeline using Amazon Bedrock and Amazon Nova foundation models, achieving 98% classification accuracy while reducing costs by 77% and processing time by 80%. We detail the technical implementation using AWS's open-source GenAI Intelligent Document Processing Accelerator, the optimization strategies for document classification and key information extraction, and the measurable business impact on Myriad's prior authorization workflows.
In this post, CBRE and AWS demonstrate how they transformed property management by building a unified search and digital assistant using Amazon Bedrock, enabling professionals to access millions of documents and multiple databases through natural language queries. The solution combines Amazon Nova Pro for SQL generation and Claude Haiku for document interactions, achieving a 67% reduction in processing time while maintaining enterprise-grade security across more than eight million documents.
In this post, we introduce Managed Tiered KV Cache and Intelligent Routing for Amazon SageMaker HyperPod, new capabilities that can reduce time to first token by up to 40% and lower compute costs by up to 25% for long context prompts and multi-turn conversations. These features automatically manage distributed KV caching infrastructure and intelligent request routing, making it easier to deploy production-scale LLM inference workloads with enterprise-grade performance while significantly reducing operational overhead.
We are launching a new feature: gateway interceptors for Amazon Bedrock AgentCore Gateway. This powerful new capability provides fine-grained security, dynamic access control, and flexible schema management.
In this post, we explore how Condé Nast used Amazon Bedrock and Anthropic’s Claude to accelerate their contract processing and rights analysis workstreams. The company’s extensive portfolio, spanning multiple brands and geographies, required managing an increasingly complex web of contracts, rights, and licensing agreements.
Available through the Amazon Bedrock bidirectional streaming API, Amazon Nova Sonic can connect to your business data and external tools and can be integrated directly with telephony systems. This post will introduce sample implementations for the most common telephony scenarios.
In this post, we will walk through the performance constraints and design choices by OARC and REMAP teams at UCLA, including how AWS serverless infrastructure, AWS Managed Services, and generative AI services supported the rapid design and deployment of our solution. We will also describe our use of Amazon SageMaker AI and how it can be used reliably in immersive live experiences.
This post is written by Chaim Rand, Principal Engineer, Pini Reisman, Software Senior Principal Engineer, and Eliyah Weinberg, Performance and Technology Innovation Engineer, at Mobileye. The Mobileye team would like to thank Sunita Nadampalli and Guy Almog from AWS for their contributions to this solution and this post. Mobileye is driving the global evolution toward […]
This blog post introduces the new Amazon Nova model evaluation features in Amazon SageMaker AI. This release adds custom metrics support, LLM-based preference testing, log probability capture, metadata analysis, and multi-node scaling for large evaluations.
You can now achieve significant performance improvements when using Amazon Bedrock Custom Model Import, with reduced end-to-end latency, faster time-to-first-token, and improved throughput through advanced PyTorch compilation and CUDA graph optimizations. With Amazon Bedrock Custom Model Import you can to bring your own foundation models to Amazon Bedrock for deployment and inference at scale. In this post, we introduce how to use the improvements in Amazon Bedrock Custom Model Import.
Amazon SageMaker AI now supports EAGLE-based adaptive speculative decoding, a technique that accelerates large language model inference by up to 2.5x while maintaining output quality. In this post, we explain how to use EAGLE 2 and EAGLE 3 speculative decoding in Amazon SageMaker AI, covering the solution architecture, optimization workflows using your own datasets or SageMaker's built-in data, and benchmark results demonstrating significant improvements in throughput and latency.
In this post, we demonstrate how to migrate computer vision workloads from Amazon Lookout for Vision to Amazon SageMaker AI by training custom defect detection models using pre-trained models available on AWS Marketplace. We provide step-by-step guidance on labeling datasets with SageMaker Ground Truth, training models with flexible hyperparameter configurations, and deploying them for real-time or batch inference—giving you greater control and flexibility for automated quality inspection use cases.
The AWS Customer Success Center of Excellence (CS COE) helps customers get tangible value from their AWS investments. We've seen a pattern: customers who build AI strategies that address people, process, and technology together succeed more often. In this post, we share practical considerations that can help close the AI value gap.
We're introducing bidirectional streaming for Amazon SageMaker AI Inference, which transforms inference from a transactional exchange into a continuous conversation. This post shows you how to build and deploy a container with bidirectional streaming capability to a SageMaker AI endpoint. We also demonstrate how you can bring your own container or use our partner Deepgram's pre-built models and containers on SageMaker AI to enable bi-directional streaming feature for real-time inference.
Warner Bros. Discovery (WBD) is a leading global media and entertainment company that creates and distributes the world’s most differentiated and complete portfolio of content and brands across television, film and streaming. In this post, we describe the scale of our offerings, artificial intelligence (AI)/machine learning (ML) inference infrastructure requirements for our real time recommender systems, and how we used AWS Graviton-based Amazon SageMaker AI instances for our ML inference workloads and achieved 60% cost savings and 7% to 60% latency improvements across different models.
In this post, we explore the complete development lifecycle of physical AI—from data collection and model training to edge deployment—and examine how these intelligent systems learn to understand, reason, and interact with the physical world through continuous feedback loops. We illustrate this workflow through Diligent Robotics' Moxi, a mobile manipulation robot that has completed over 1.2 million deliveries in hospitals, saving nearly 600,000 hours for clinical staff while transforming healthcare logistics and returning valuable time to patient care.
In this post, we explore how Amazon SageMaker HyperPod now supports NVIDIA Multi-Instance GPU (MIG) technology, enabling you to partition powerful GPUs into multiple isolated instances for running concurrent workloads like inference, research, and interactive development. By maximizing GPU utilization and reducing wasted resources, MIG helps organizations optimize costs while maintaining performance isolation and predictable quality of service across diverse machine learning tasks.
We are excited to announce that customers in Canada can now access advanced foundation models including Anthropic's Claude Sonnet 4.5 and Claude Haiku 4.5 on Amazon Bedrock through cross-Region inference (CRIS). This post explores how Canadian organizations can use cross-Region inference profiles from the Canada (Central) Region to access the latest foundation models to accelerate AI initiatives. We will demonstrate how to get started with these new capabilities, provide guidance for migrating from older models, and share recommended practices for quota management.
Amazon SageMaker HyperPod clusters with Amazon Elastic Kubernetes Service (EKS) orchestration now support creating and managing interactive development environments such as JupyterLab and open source Visual Studio Code, streamlining the ML development lifecycle by providing managed environments for familiar tools to data scientists. This post shows how HyperPod administrators can configure Spaces for their clusters, and how data scientists can create and connect to these Spaces.
Anthropic's newest foundation model, Claude Opus 4.5, is now available in Amazon Bedrock, a fully managed service that offers a choice of high-performing foundation models from leading AI companies. In this post, I'll show you what makes this model different, walk through key business applications, and demonstrate how to use Opus 4.5's new tool use capabilities on Amazon Bedrock.
In this post, we show how to deploy the GPT-OSS-20B model on Amazon Bedrock using Custom Model Import while maintaining complete API compatibility with your current applications.
In this post, we introduce the Multi-Provider Generative AI Gateway reference architecture, which provides guidance for deploying LiteLLM into an AWS environment to streamline the management and governance of production generative AI workloads across multiple model providers. This centralized gateway solution addresses common enterprise challenges including provider fragmentation, decentralized governance, operational complexity, and cost management by offering a unified interface that supports Amazon Bedrock, Amazon SageMaker AI, and external providers while maintaining comprehensive security, monitoring, and control capabilities.
In this post, you'll learn how to deploy geospatial AI agents that can answer complex spatial questions in minutes instead of months. By combining Foursquare Spatial H3 Hub's analysis-ready geospatial data with reasoning models deployed on Amazon SageMaker AI, you can build agents that enable nontechnical domain experts to perform sophisticated spatial analysis through natural language queries—without requiring geographic information system (GIS) expertise or custom data engineering pipelines.
In this post, we share how Wipro implemented advanced prompt engineering techniques, custom validation logic, and automated code rectification to streamline the development of industrial automation code at scale using Amazon Bedrock. We walk through the architecture along with the key use cases, explain core components and workflows, and share real-world results that show the transformative impact on manufacturing operations.
This blog post has explores how MSD is harnessing the power of generative AI and databases to optimize and transform its manufacturing deviation management process. By creating an accurate and multifaceted knowledge base of past events, deviations, and findings, the company aims to significantly reduce the time and effort required for each new case while maintaining the highest standards of quality and compliance.
In this blog post, we show you how agentic workflows can accelerate the processing and interpretation of genomics pipelines at scale with a natural language interface. We demonstrate a comprehensive genomic variant interpreter agent that combines automated data processing with intelligent analysis to address the entire workflow from raw VCF file ingestion to conversational query interfaces.
Our team at Amazon builds Rufus, an AI-powered shopping assistant which delivers intelligent, conversational experiences to delight our customers. More than 250 million customers have used Rufus this year. Monthly users are up 140% YoY and interactions are up 210% YoY. Additionally, customers that use Rufus during a shopping journey are 60% more likely to […]
In this post, we demonstrate how healthcare organizations can securely implement prompt caching technology to streamline medical record processing while maintaining compliance requirements.
In this post, we explore deployment patterns and best practices for Claude Code with Amazon Bedrock, covering authentication methods, infrastructure decisions, and monitoring strategies to help enterprises deploy securely at scale. We recommend using Direct IdP integration for authentication, a dedicated AWS account for infrastructure, and OpenTelemetry with CloudWatch dashboards for comprehensive monitoring to ensure secure access, capacity management, and visibility into costs and developer productivity .
Amazon Bedrock Guardrails now extends its safety controls to protect code generation across twelve programming languages, addressing critical security challenges in AI-assisted software development. In this post, we explore how to configure content filters, prompt attack detection, denied topics, and sensitive information filters to safeguard against threats like prompt injection, data exfiltration, and malicious code generation while maintaining developer productivity .
Today, we're announcing the AWS Well-Architected Responsible AI Lens—a set of thoughtful questions and corresponding best practices that help builders address responsible AI concerns throughout development and operation.
Amazon's AI-powered Amazon Compliance Screening system tackles complex compliance challenges through autonomous agents that analyze, reason through, and resolve cases with precision. This blog post explores how Amazon’s Compliance team built its AI-powered investigation system through a series of AI agents built on AWS.
In this post, we cover how you can use tools from Snowflake AI Data Cloud and Amazon Web Services (AWS) to build generative AI solutions that organizations can use to make data-driven decisions, increase operational efficiency, and ultimately gain a competitive edge.
In this post you will learn how to use Spectrum to optimize resource use and shorten training times without sacrificing quality, as well as how to implement Spectrum fine-tuning with Amazon SageMaker AI training jobs. We will also discuss the tradeoff between QLoRA and Spectrum fine-tuning, showing that while QLoRA is more resource efficient, Spectrum results in higher performance overall.
RoboTic-Tac-Toe is an interactive game where two physical robots move around a tic-tac-toe board, with both the gameplay and robots’ movements orchestrated by LLMs. Players can control the robots using natural language commands, directing them to place their markers on the game board. In this post, we explore the architecture and prompt engineering techniques used to reason about a tic-tac-toe game and decide the next best game strategy and movement plan for the current player.
This blog post introduces two major enhancements to Amazon SageMaker HyperPod that strengthen security and storage capabilities for large-scale machine learning infrastructure. The new features include customer managed key (CMK) support for encrypting EBS volumes with organization-controlled encryption keys, and Amazon EBS CSI driver integration that enables dynamic storage management for Kubernetes volumes in AI workloads.
In this post, I will illustrate how applying platform engineering principles to generative AI unlocks faster time-to-value, cost control, and scalable innovation.
This year, re:Invent will be held in Las Vegas, Nevada, from December 1 to December 5, 2025, and this guide will help you navigate our comprehensive session catalog and plan your week. The sessions cater to business and technology leaders, product and engineering teams, and data and analytics teams interested in incorporating agentic AI capabilities across their teams and organization.
I'm excited to announce AWS Professional Services now offers specialized AI agents including the AWS Professional Services Delivery Agent. This represents a transformation to the consulting experience that embeds intelligent agents throughout the consulting life cycle to deliver better value for customers.
In this post, we explore how Amazon Bedrock AgentCore and Claude are enabling enterprises like Cox Automotive and Druva to deploy production-ready agentic AI systems that deliver measurable business value, with results including up to 63% autonomous issue resolution and 58% faster response times. We examine the technical foundation combining Claude's frontier AI capabilities with AgentCore's enterprise-grade infrastructure that allows organizations to focus on agent logic rather than building complex operational systems from scratch.
In this post, we demonstrate how to build a production-ready biomedical research agent by integrating Biomni's specialized tools with Amazon Bedrock AgentCore Gateway, enabling researchers to access over 30 biomedical databases through a secure, scalable infrastructure. The implementation showcases how to transform research prototypes into enterprise-grade systems with persistent memory, semantic tool discovery, and comprehensive observability for scientific reproducibility .
Graphical user interfaces have carried the torch for decades, but today’s users increasingly expect to talk to their applications. In this post we show how we added a true voice-first experience to a reference application—the Smart Todo App—turning routine task management into a fluid, hands-free conversation.
Generative AI is transforming the way businesses interact with their customers and revolutionizing conversational interfaces for complex IT operations. Druva, a leading provider of data security solutions, is at the forefront of this transformation. In collaboration with Amazon Web Services (AWS), Druva is developing a cutting-edge generative AI-powered multi-agent copilot that aims to redefine the customer experience in data security and cyber resilience.
In this post, we demonstrate how you can use the A2A protocol for AI agents built with different frameworks to collaborate seamlessly. You'll learn how to deploy A2A servers on AgentCore Runtime, configure agent discovery and authentication, and build a real-world multi-agent system for incident response. We'll cover the complete A2A request lifecycle, from agent card discovery to task delegation, showing how standardized protocols eliminate the complexity of multi-agent coordination.
The Cohere Embed 4 multimodal embeddings model is now available as a fully managed, serverless option in Amazon Bedrock. In this post, we dive into the benefits and unique capabilities of Embed 4 for enterprise search use cases. We’ll show you how to quickly get started using Embed 4 on Amazon Bedrock, taking advantage of integrations with Strands Agents, S3 Vectors, and Amazon Bedrock AgentCore to build powerful agentic retrieval-augmented generation (RAG) workflows.
The regulatory landscape for GxP compliance is evolving to address the unique characteristics of AI. Traditional Computer System Validation (CSV) approaches, often with uniform validation strategies, are being supplemented by Computer Software Assurance (CSA) frameworks that emphasize flexible risk-based validation methods tailored to each system's actual impact and complexity (FDA latest guidance). In this post, we cover a risk-based implementation, practical implementation considerations across different risk levels, the AWS shared responsibility model for compliance, and concrete examples of risk mitigation strategies.
In this post, we explore four key collaboration patterns for multi-agent, multimodal AI systems – Agents as Tools, Swarms Agents, Agent Graphs, and Agent Workflows – and discuss when and how to apply each using the open-source AWS Strands Agents SDK with Amazon Nova models.
In this post, we demonstrate that fine-tuning VLMs provides a powerful and flexible approach to automate and significantly enhance document understanding capabilities. We also demonstrate that using focused fine-tuning allows smaller, multi-modal models to compete effectively with much larger counterparts (98% accuracy with Qwen2.5 VL 3B).
In this post, we demonstrate how Clario has used Amazon Bedrock and other AWS services to build an AI-powered solution that automates and improves the analysis of COA interviews.
Organizations need seamless access to their structured data repositories to power intelligent AI agents. However, when these resources span multiple AWS accounts integration challenges can arise. This post explores a practical solution for connecting Amazon Bedrock agents to knowledge bases in Amazon Redshift clusters residing in different AWS accounts.
In this blog post, we explore how TR addressed key business use cases with Open Arena, a highly scalable and flexible no-code AI solution powered by Amazon Bedrock and other AWS services such as Amazon OpenSearch Service, Amazon Simple Storage Service (Amazon S3), Amazon DynamoDB, and AWS Lambda. We'll explain how TR used AWS services to build this solution, including how the architecture was designed, the use cases it solves, and the business profiles that use it.
Today, we are excited to announce the addition of structured output to Custom Model Import. Structured output constrains a model's generation process in real time so that every token it produces conforms to a schema you define. Rather than relying on prompt-engineering tricks or brittle post-processing scripts, you can now generate structured outputs directly at inference time.
Earlier this year, we introduced Amazon Bedrock AgentCore Gateway, a fully managed service that serves as a centralized MCP tool server, providing a unified interface where agents can discover, access, and invoke tools. Today, we're extending support for existing MCP servers as a new target type in AgentCore Gateway. With this capability, you can group multiple task-specific MCP servers aligned to agent goals behind a single, manageable MCP gateway interface. This reduces the operational complexity of maintaining separate gateways, while providing the same centralized tool and authentication management that existed for REST APIs and AWS Lambda functions.