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 .  ( 127 min )

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.  ( 120 min )

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.  ( 123 min )

凤鸣山问丹 上虞的秋日，凤鸣山薄雾如纱。我沿石阶缓步而上，两旁古木参天，溪水泠泠作响，仿佛仍回荡着千年前炉火噼啪的余音。山腰处，一方“炼丹井”静卧于苔痕斑驳的石栏内，井水幽深，映不出魏伯阳的身影，却照见自己模糊的轮廓——这方寸水土，曾是他与弟子们埋首炼丹、叩问长生的地方。 山间传说里，魏伯阳炼成金丹后，以犬试药，犬倒地如死。两位弟子心生疑惧，弃丹而去；唯有一人笃信师道，愿同服共死。结果师徒与犬皆复苏飞升，而犹豫者终老山下。故事如山风拂过耳际，初听是仙迹，细思却如井水般冰凉：那“坚定”的信念，究竟该交付给谁？若丹本为毒，那“信”岂非成了引向深渊的绳索？ 下山途中，偶遇一位老农在田埂上歇息。他笑谈：“如今谁还信什么金丹？但人总得信点什么吧，不然日子怎么过？”他信的是节气、是土地、是春种秋收的踏实。这朴素之“尚”，与魏伯阳的玄奥丹道相隔千年，却同样支撑着一种生活。吴晗先生曾言，社会风气之“尚”如潮汐涨落，或尚名节，或尚功利，或尚清谈——可无论何种“尚”，若只知随波逐流，不加省察，便如那两位弃丹弟子，既失了飞升之机，也未必真得了安稳。 归途车窗外，城市灯火渐次亮起，霓虹如新的“丹炉”，闪烁着财富、流量、速度的诱人光泽。我们这一代人，何尝不在各自的时代“炼丹”？只是炉中所炼，早已不是铅汞，而是对意义、价值与归属的渴求。然而，若只知追逐那最耀眼的光，却不肯停下脚步自问一句“此丹可服否？”，恐怕终将陷入另一种“假死”——身体活着，灵魂却已沉睡。 凤鸣山无凤鸣，唯有风过林梢。魏伯阳的丹炉早已冷透，但那口炼丹井却像一面古镜，照见所有时代人心深处的叩问：我们该信什么？又为何而信？ 苏格拉底说：“未经省察的人生不值得过。”或许真正的“丹”，并非服食之物，而是那敢于审视自身信念的勇气——它不许诺飞升，却能让双脚在尘世站得更稳，让眼睛在迷雾中看得更清。  ( 1 min )

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.  ( 126 min )

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.  ( 123 min )

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.  ( 125 min )

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.  ( 131 min )

Background We build a bunch of stuff for RISC-V using the Dart official Docker image, but the RISC-V images can often arrive some time (days) after the more mainstream images[1]. That means that if we merge a Dependabot PR for an updated image it might well be missing RISC-V, causing the Continuous Delivery (CD) pipeline […]  ( 12 min )

Background We build a bunch of stuff for RISC-V using the Dart official Docker image, but the RISC-V images can often arrive some time (days) after the more mainstream images[1]. That means that if we merge a Dependabot PR for an updated image it might well be missing RISC-V, causing the Continuous Delivery (CD) pipeline […]  ( 12 min )

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).  ( 132 min )

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.  ( 121 min )

View on sreweekly.com A message from our sponsor, CodeRabbit: CodeRabbit is your AI co-pilot for code reviews. Get instant code review feedback, one-click fix suggestions and define custom rules with AST Grep to catch subtle issues static tools miss. Trusted across 1M repos and 70K open-source projects. ☞ Get Started Today The hidden trade-offs of […]  ( 4 min )

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.  ( 122 min )

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.  ( 123 min )

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.  ( 121 min )

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.  ( 127 min )

In this post, we show you how Amazon Search optimized GPU instance utilization by leveraging AWS Batch for SageMaker Training jobs. This managed solution enabled us to orchestrate machine learning (ML) training workloads on GPU-accelerated instance families like P5, P4, and others. We will also provide a step-by-step walkthrough of the use case implementation.  ( 124 min )

TL;DR Agentic systems are the latest thing being used to solve IT integration issues, becoming the glue squirted into the gaps between systems. But the use of natural language means that the distinction between ‘data’ and ‘code’ is almost impossible to make, which causes a whole raft of security concerns. This new glue may be […]  ( 13 min )

TL;DR Agentic systems are the latest thing being used to solve IT integration issues, becoming the glue squirted into the gaps between systems. But the use of natural language means that the distinction between ‘data’ and ‘code’ is almost impossible to make, which causes a whole raft of security concerns. This new glue may be […]  ( 13 min )

Amazon Bedrock AgentCore is an agentic platform for building, deploying, and operating effective agents securely at scale. Amazon Bedrock AgentCore Runtime is a fully managed service of Bedrock AgentCore, which provides low latency serverless environments to deploy agents and tools. It provides session isolation, supports multiple agent frameworks including popular open-source frameworks, and handles multimodal […]  ( 120 min )

In this post, we examine the specific challenges Switchboard, MD faced with scaling transcription accuracy and cost-effectiveness in clinical environments, their evaluation process for selecting the right transcription solution, and the technical architecture they implemented using Amazon Connect and Amazon Kinesis Video Streams. This post details the impressive results achieved and demonstrates how they were able to use this foundation to automate EMR matching and give healthcare staff more time to focus on patient care.  ( 119 min )

Pupdate The central heating went on a few days into the month, and it was also soon time for the boys to be wearing their coats out. Interactive Ball Toy Having learned my lesson about dodgy drop shippers last month I ordered from AliExpress when $wife found a fun looking toy in some Dachshund forum. […]  ( 14 min )

Pupdate The central heating went on a few days into the month, and it was also soon time for the boys to be wearing their coats out. Interactive Ball Toy Having learned my lesson about dodgy drop shippers last month I ordered from AliExpress when $wife found a fun looking toy in some Dachshund forum. […]  ( 14 min )

View on sreweekly.com I’m back! Kidney donation was a fascinating and rewarding experience, and I encourage you to learn more. It’s amazing how it’s possible to fix one human with spare parts from another! I’ll share more about my experience later, but for now: thank you to the many of you that reached out with […]  ( 4 min )

Enterprises in regulated industries often need mathematical certainty that every AI response complies with established policies and domain knowledge. Regulated industries can’t use traditional quality assurance methods that test only a statistical sample of AI outputs and make probabilistic assertions about compliance. When we launched Automated Reasoning checks in Amazon Bedrock Guardrails in preview at […]  ( 132 min )

In 2024, we launched the Custom Model Program within the AWS Generative AI Innovation Center to provide comprehensive support throughout every stage of model customization and optimization. Over the past two years, this program has delivered exceptional results by partnering with global enterprises and startups across diverse industries—including legal, financial services, healthcare and life sciences, […]  ( 123 min )

This post builds upon our previous post discussing how Clario developed an AI solution powered by Amazon Bedrock to accelerate clinical trials. Since then, Clario has further enhanced their AI capabilities, focusing on innovative solutions that streamline the generation of software configurations and artifacts for clinical trials while delivering high-quality clinical evidence.  ( 123 min )

こんにちは, G’day. The recent launch of Anthropic’s Claude Sonnet 4.5 and Claude Haiku 4.5, now available on Amazon Bedrock, marks a significant leap forward in generative AI models. These state-of-the-art models excel at complex agentic tasks, coding, and enterprise workloads, offering enhanced capabilities to developers. Along with the new models, we are thrilled to announce that […]  ( 123 min )

AI agents need to browse the web on your behalf. When your agent visits a website to gather information, complete a form, or verify data, it encounters the same defenses designed to stop unwanted bots: CAPTCHAs, rate limits, and outright blocks. Today, we are excited to share that AWS has a solution. Amazon Bedrock AgentCore […]  ( 119 min )

In this post, we explore how to deploy NVIDIA's Parakeet ASR model on Amazon SageMaker AI using asynchronous inference endpoints to create a scalable, cost-effective pipeline for processing large volumes of audio data. The solution combines state-of-the-art speech recognition capabilities with AWS managed services like Lambda, S3, and Bedrock to automatically transcribe audio files and generate intelligent summaries, enabling organizations to unlock valuable insights from customer calls, meeting recordings, and other audio content at scale .  ( 126 min )

TL;DR Supply-chain Levels for Software Artifacts (SLSA) attestations are a great way to show that you care about security, and they’re fairly trivial to add to delivery pipelines that produce a single binary or container image. But things get tricky with matrix jobs that build lots of things in parallel, as you then need to […]  ( 14 min )

TL;DR Supply-chain Levels for Software Artifacts (SLSA) attestations are a great way to show that you care about security, and they’re fairly trivial to add to delivery pipelines that produce a single binary or container image. But things get tricky with matrix jobs that build lots of things in parallel, as you then need to […]  ( 14 min )

In this post, we explore the critical design considerations for building responsible AI systems in healthcare and life sciences, focusing on establishing governance mechanisms, transparency artifacts, and security measures that ensure safe and effective generative AI applications. The discussion covers essential policies for mitigating risks like confabulation and bias while promoting trust, accountability, and patient safety throughout the AI development lifecycle.  ( 121 min )

In this post, we explore the Five V's Framework—a field-tested methodology that has helped 65% of AWS Generative AI Innovation Center customer projects successfully transition from concept to production, with some launching in just 45 days. The framework provides a structured approach through Value, Visualize, Validate, Verify, and Venture phases, shifting focus from "What can AI do?" to "What do we need AI to do?" while ensuring solutions deliver measurable business outcomes and sustainable operational excellence.  ( 122 min )

In this post, we explore an innovative approach that converts natural language to Gremlin queries using Amazon Bedrock models such as Amazon Nova Pro, helping business analysts and data scientists access graph databases without requiring deep technical expertise. The methodology involves three key steps: extracting graph knowledge, structuring the graph similar to text-to-SQL processing, and generating executable Gremlin queries through an iterative refinement process that achieved 74.17% overall accuracy in testing.  ( 122 min )

In this post, we explore how companies can systematically incorporate responsible AI practices into their generative AI project prioritization methodology to better evaluate business value against costs while addressing novel risks like hallucination and regulatory compliance. The post demonstrates through a practical example how conducting upfront responsible AI risk assessments can significantly change project rankings by revealing substantial mitigation work that affects overall project complexity and timeline.  ( 120 min )

In this post, we explore how product teams can leverage Amazon Bedrock and AWS services to transform their creative workflows through generative AI, enabling rapid content iteration across multiple formats while maintaining brand consistency and compliance. The solution demonstrates how teams can deploy a scalable generative AI application that accelerates everything from product descriptions and marketing copy to visual concepts and video content, significantly reducing time to market while enhancing creative quality.  ( 123 min )

In this post, we explore advanced cost monitoring strategies for Amazon Bedrock deployments, introducing granular custom tagging approaches for precise cost allocation and comprehensive reporting mechanisms that build upon the proactive cost management foundation established in Part 1. The solution demonstrates how to implement invocation-level tagging, application inference profiles, and integration with AWS Cost Explorer to create a complete 360-degree view of generative AI usage and expenses.  ( 121 min )

In this post, we introduce a comprehensive solution for proactively managing Amazon Bedrock inference costs through a cost sentry mechanism designed to establish and enforce token usage limits, providing organizations with a robust framework for controlling generative AI expenses. The solution uses serverless workflows and native Amazon Bedrock integration to deliver a predictable, cost-effective approach that aligns with organizational financial constraints while preventing runaway costs through leading indicators and real-time budget enforcement.  ( 122 min )

In this post, we demonstrate how Amazon Nova Premier with Amazon Bedrock can systematically migrate legacy C code to modern Java/Spring applications using an intelligent agentic workflow that breaks down complex conversions into specialized agent roles. The solution reduces migration time and costs while improving code quality through automated validation, security assessment, and iterative refinement processes that handle even large codebases exceeding token limitations.  ( 131 min )

In this post, we detail how Metagenomi partnered with AWS to implement the Progen2 protein language model on AWS Inferentia, achieving up to 56% cost reduction for high-throughput enzyme generation workflows. The implementation enabled cost-effective generation of millions of novel enzyme variants using EC2 Inf2 Spot Instances and AWS Batch, demonstrating how cloud-based generative AI can make large-scale protein design more accessible for biotechnology applications .  ( 123 min )

In this post, we walk through how to take an ML model built in SageMaker Canvas and deploy it using SageMaker Serverless Inference, helping you go from model creation to production-ready predictions quickly and efficiently without managing any infrastructure. This solution demonstrates a complete workflow from adding your trained model to the SageMaker Model Registry through creating serverless endpoint configurations and deploying endpoints that automatically scale based on demand .  ( 40 min )

In this post, we explore how Amazon Nova Sonic's speech-to-speech capabilities can be combined with Amazon Bedrock AgentCore to create sophisticated multi-agent voice assistants that break complex tasks into specialized, manageable components. The approach demonstrates how to build modular, scalable voice applications using a banking assistant example with dedicated sub-agents for authentication, banking inquiries, and mortgage services, offering a more maintainable alternative to monolithic voice assistant designs.  ( 38 min )

In this post, we demonstrate how to deploy and manage machine learning training workloads using the Amazon SageMaker HyperPod training operator, which enhances training resilience for Kubernetes workloads through pinpoint recovery and customizable monitoring capabilities. The Amazon SageMaker HyperPod training operator helps accelerate generative AI model development by efficiently managing distributed training across large GPU clusters, offering benefits like centralized training process monitoring, granular process recovery, and hanging job detection that can reduce recovery times from tens of minutes to seconds.  ( 41 min )