View on sreweekly.com A message from our sponsor, atscaleconference.com: Building scalable, high-performance infrastructure for AI is one of today’s toughest challenges. Join @Scale: Systems & Reliability on June 25 in Bellevue, WA to learn how leading engineers are solving it. Secure your seat today! The Silent Failure of Reliability Metrics at Scale: Lessons Learned from […]  ( 4 min )

In this post, we walk through the full journey, from setting up your migration workspace in AWS Transform to subscribing to partner agents through AWS Marketplace to unlocking Amazon Quick capabilities that change how your organization consumes data.  ( 112 min )

Pupdate It’s been mostly warm and dry, so plenty of opportunities for longer walks :) Milo is now on the final cycle of his 4th chemo protocol, and it’s proceeding OK. Toronto We started the month in Toronto, which was a really fun trip deserving it’s own post. Eyes My cataracts are gone, and I […]  ( 14 min )

Pupdate It’s been mostly warm and dry, so plenty of opportunities for longer walks :) Milo is now on the final cycle of his 4th chemo protocol, and it’s proceeding OK. Toronto We started the month in Toronto, which was a really fun trip deserving it’s own post. Eyes My cataracts are gone, and I […]  ( 14 min )

人在职场不快乐，只因未读苏东坡 林语堂在《苏东坡传》里说，苏东坡的人生，是从四十岁之后开始的。如今年过四十的我，每当职场内卷不快乐的时候，我都能从苏东坡的诗词里找到慰藉和力量。 今天的职场，很多压力和焦虑看似新鲜，实则古已有之。趁着五一闲暇，抄写一首《满庭芳》，可以说是苏老的“职场反内卷宣言”，让我产生些许共鸣。并对照当下职场做了一份“职场解压版”，希望它能提醒你：真正重要的，不是无休止的竞争，而是给自己留一点生活的余地。 职场解压版 KPI虚名，年终微利，算来著甚干忙（PA 晋升、各种评奖……为了这点虚名微利，算来算去，值得把自己忙成这样吗）。 晋升前定，谁卷谁又强。（你以为晋升靠拼命，其实很多时候和能力无关） 且趁40未老，尽放我、些子疏狂（趁还没被996榨干，保留一点”不服从”的野性，夜晚非老板电话不接消息不回，周报里敢写牢骚）。 百年里，浑教是醉，三万六千场。（一辈子也就三万六千天，偶尔放松，比天天紧绷更可贵） 思量。能几许，忧愁风雨，一半相妨。（想想吧，焦虑内耗至少偷走了一半人生，值得吗） 又何须，抵死说短道长。（何必互相甩锅，各种损招？） 幸对清风皓月，奶茶店、云幕高张。（真正的”福利”是下班后的清风明月，路边的奶茶小店，天边的晚霞） 下班好，千钟美酒，一曲满庭芳。（下班真好，和朋友喝顿酒，唱首歌，这才是自己的人生） 为什么今日依然可参考 苏东坡的心态提醒我们，工作只是人生的一部分。你可以努力，但不必把自己逼成机器；你可以认真，却不必把时间和情绪都交给职场。 这不是鼓励你消极避工，而是鼓励你在职场中保留自我。用苏东坡的方式看待压力，不是逃避，而是给自己多一份选择：内卷之外，还有更多值得好好过的日子。人生不只有绩效，还有在忙碌之外的安静时刻。 愿你这个五一，既能放松心情，也能找到属于自己的“满庭芳”。  ( 1 min )

In this post, we take a deeper look at how RLAIF or RL with LLM-as-a-judge works with Amazon Nova models effectively.  ( 115 min )

In this post, we introduce a systematic framework for LLM migration or upgrade in generative AI production, encompassing essential tools, methodologies, and best practices. The framework facilitates transitions between different LLMs by providing robust protocols for prompt conversion and optimization.  ( 125 min )

In this post, we show how Sun Finance used Amazon Bedrock, Amazon Textract, and Amazon Rekognition to build an AI-powered identity verification (IDV) pipeline. The solution improved extraction accuracy from 79.7% to 90.8%, cut per-document costs by 91%, and reduced processing time from up to 20 hours to under 5 seconds. You'll learn how combining specialized OCR with large language model (LLM) structuring outperformed using either tool alone. You'll also learn how to architect a serverless fraud detection system using vector similarity search.  ( 117 min )

This post demonstrates how agentic AI assistant from Amazon Quick transform data analytics into a self-service capability by using Amazon Simple Storage Service (Amazon S3) as a storage, Amazon SageMaker and AWS Glue for lakehouse, Amazon Athena for serverless SQL querying across multiple storage formats (S3 Table, Iceberg, and Parquet).  ( 122 min )

In this post, you will configure Amazon Bedrock AgentCore Gateway to access private endpoints using Resource Gateway, a managed construct that provisions Elastic Network Interfaces (ENIs) directly inside your Amazon VPC, one per subnet. You will explore two implementation modes (managed and self-managed) and walk through three practical scenarios: connecting to a private Amazon API Gateway endpoint, integrating with a MCP server on Amazon Elastic Kubernetes Service (Amazon EKS), and accessing a private REST API.  ( 113 min )

This post was co-written with Yash Munsadwala, Adam Hood, Justin Guse, and Hector Hernandez from PwC. Contract analysis often consumes significant time for legal, compliance, and procurement teams, especially when important insights are buried in lengthy, unstructured agreements. As contract volumes grow, finding specific clauses and assessing extracted terms can become increasingly difficult to scale. […]  ( 113 min )

In this post, you will learn how to design namespace hierarchies, choose the right retrieval patterns, and implement AWS Identity and Access Management (IAM)-based access control for AgentCore Memory.  ( 112 min )

In this post, you'll learn how Vanguard built their Virtual Analyst solution by focusing on eight guiding principles of AI-ready data, the AWS services that powered their implementation, and the measurable business outcomes they achieved.  ( 111 min )

This post shows you how to deploy a serverless MCP proxy on Amazon Bedrock AgentCore Runtime that gives you a programmable layer to implement proper governance, controls, and observability aligned with an organization's security policies.  ( 116 min )

TL;DR Toronto is a fantastic city, with plenty to keep us entertained over our 6 night stay. Why Toronto? We’d originally talked about returning to Halifax Nova Scotia, which we last visited in 2000; and then $wife announced that she’d like to go somewhere new. Getting there We picked flights with Air Canada on their […]  ( 16 min )

TL;DR Toronto is a fantastic city, with plenty to keep us entertained over our 6 night stay. Why Toronto? We’d originally talked about returning to Halifax Nova Scotia, which we last visited in 2000; and then $wife announced that she’d like to go somewhere new. Getting there We picked flights with Air Canada on their […]  ( 16 min )

In this post, we explore what it takes to migrate a traditional text agent into a conversational voice assistant using Amazon Nova 2 Sonic. We compare text and voice agent requirements, highlight design priorities for different use cases, break down agent architecture, and address common concerns like tools and sub-agents for reuse and system prompt adaptation. This post helps you navigate the migration process and avoid common pitfalls.  ( 113 min )

Today, we are excited to announce the day zero availability of NVIDIA Nemotron 3 Nano Omni on Amazon SageMaker JumpStart. In this post, we walk through the model architecture and key capabilities of Nemotron 3 Nano Omni, explore the enterprise use cases it unlocks, and show you how to deploy and run inference using Amazon SageMaker JumpStart.  ( 109 min )

This post shows you how to build your first AI-powered workflow, using Amazon Quick, starting with a financial analysis tool and progressing to an advanced employee onboarding automation.  ( 115 min )

In this post, we explore an automated solution that detects S3 events and triggers ingestion jobs while respecting service quotas and providing comprehensive monitoring. This serverless solution uses an event-driven architecture to keep your knowledge base current without overwhelming the Amazon Bedrock APIs.  ( 114 min )

In this post, we demonstrate how to build AI agents using Strands Agents SDK with models deployed on SageMaker AI endpoints. You will learn how to deploy foundation models from SageMaker JumpStart, integrate them with Strands Agents, and establish production-grade observability using SageMaker Serverless MLflow for agent tracing. We also cover how to implement A/B testing across multiple model variants and evaluate agent performance using MLflow metrics and show how you can build, deploy, and continuously improve AI agents on infrastructure you control.  ( 115 min )

In this post, we share how we applied Amazon Bedrock and the Amazon Nova family of models to reimagine our Title Suggestion feature. By combining metadata, computer vision, and retrieval-augmented generative AI, we now automatically generate creative, brand-aligned titles and subtitles across 12 languages. Using the unified API of Amazon Bedrock, Anthropic’s Claude 3 Haiku, and Amazon Nova Lite and Pro, we improved quality, reduced cost, and cut response times. This resulted in higher customer satisfaction, measurable uplifts in engagement and purchase rates, and over 5.5 million personalised titles generated in 2025.  ( 111 min )

View on sreweekly.com How we built a real-world evaluation platform for autonomous SRE agents at scale Finally! Someone actually explaining how they test their SRE agent. Having a testing methodology is table stakes. Showing their work helps us decide whether we can trust the tool. With so many SRE agents floating around, it’s quite surprising […]  ( 4 min )

In this post, we show how connecting the Visier Workforce AI platform with Amazon Quick through Model Context Protocol (MCP) gives every knowledge worker a unified agentic workspace to ask questions in. Visier helps ground the workspace in live workforce data and the organizational context that surrounds it while letting your users act on the conversational results without switching tools.  ( 117 min )

Amazon Quick changes how you work. You can set it up in minutes and by the end of the day, you will wonder how you ever worked without it. Quick connects with your applications, tools, and data, creating a personal knowledge graph that learns your priorities, preferences, and network.  ( 109 min )

In this post, we'll explore how multimodal BioFMs work, showcase real-world applications in drug discovery and clinical development, and contextualize how AWS enables organizations to build and deploy multimodal BioFMs.  ( 113 min )

In this post, we walk through building a scalable, event-driven transcription pipeline that automatically processes audio files uploaded to Amazon Simple Storage Service (Amazon S3), and show you how to use Amazon EC2 Spot Instances and buffered streaming inference to further reduce costs.  ( 111 min )

Today, Amazon SageMaker AI  supports optimized generative AI inference recommendations. By delivering validated, optimal deployment configurations with performance metrics, Amazon SageMaker AI keeps your model developers focused on building accurate models, not managing infrastructure.  ( 114 min )

Today, we're introducing new capabilities that further streamline the agent building experience, removing the infrastructure barriers that slow teams down at every stage of agent development from the first prototype through production deployment.  ( 108 min )

Company-wise memory in Amazon Bedrock, powered by Amazon Neptune and Mem0, provides AI agents with persistent, company-specific context—enabling them to learn, adapt, and respond intelligently across multiple interactions. TrendMicro, one of the largest antivirus software companies in the world, developed the Trend’s Companion chatbot, so their customers can explore information through natural, conversational interactions  ( 108 min )

Today, we're excited to announce Claude Cowork in Amazon Bedrock. You can now run Cowork and Claude Code Desktop through Amazon Bedrock, directly or using an LLM gateway. In this post, we walk through how Claude Cowork integrates with Amazon Bedrock and show an example of how knowledge workers use it in practice.  ( 108 min )

In this post, we show how to combine DVC (Data Version Control), Amazon SageMaker AI, and Amazon SageMaker AI MLflow Apps to build end-to-end ML model lineage. We walk through two deployable patterns — dataset-level lineage and record-level lineage — that you can run in your own AWS account using the companion notebooks.  ( 115 min )

Today, we are thrilled to announce the availability of G7e instances powered by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs on Amazon SageMaker AI. You can provision nodes with 1, 2, 4, and 8 RTX PRO 6000 GPU instances, with each GPU providing 96 GB of GDDR7 memory. This launch provides the capability to use a single-node GPU, G7e.2xlarge instance to host powerful open source foundation models (FMs) like GPT-OSS-120B, Nemotron-3-Super-120B-A12B (NVFP4 variant), and Qwen3.5-35B-A3B, offering organizations a cost-effective and high-performing option.  ( 112 min )

You can use ToolSimulator, an LLM-powered tool simulation framework within Strands Evals, to thoroughly and safely test AI agents that rely on external tools, at scale. Instead of risking live API calls that expose personally identifiable information (PII), trigger unintended actions, or settling for static mocks that break with multi-turn workflows, you can use ToolSimulator's large language model (LLM)-powered simulations to validate your agents. Available today as part of the Strands Evals Software Development Kit (SDK), ToolSimulator helps you catch integration bugs early, test edge cases comprehensively, and ship production-ready agents with confidence.  ( 113 min )

In this post, we'll show you how to build a complete omnichannel ordering system using Amazon Bedrock AgentCore, an agentic platform, to build, deploy, and operate highly effective AI agents securely at scale using any framework and foundation model and Amazon Nova 2 Sonic.  ( 114 min )

View on sreweekly.com A message from our sponsor, incident.io: “Lifting and shifting” noise to new tools just buys a different UI for the same burnout. incident.io’s migration framework prioritizes service cataloging and inventory to fix ownership, preventing team friction during the transition to a scalable on-call system. Organizational Second Hit Syndrome A previously unpublished article […]  ( 4 min )

In this post, we share how Amazon Bedrock's granular cost attribution works and walk through example cost tracking scenarios.  ( 114 min )

In this post, we show you how to use Model Distillation, a model customization technique on Amazon Bedrock, to transfer routing intelligence from a large teacher model (Amazon Nova Premier) into a much smaller student model (Amazon Nova Micro). This approach cuts inference cost by over 95% and reduces latency by 50% while maintaining the nuanced routing quality that the task demands.  ( 112 min )

In this post, we show you how to build a video semantic search solution on Amazon Bedrock using Nova Multimodal Embeddings that intelligently understands user intent and retrieves accurate video results across all signal types simultaneously. We also share a reference implementation you can deploy and explore with your own content.  ( 116 min )

This hands-on guide walks through every step of fine-tuning an Amazon Nova model with the Amazon Nova Forge SDK, from data preparation to training with data mixing to evaluation, giving you a repeatable playbook you can adapt to your own use case. This is the second part in our Nova Forge SDK series, building on the SDK introduction and first part, which covered kicking off customization experiments.  ( 114 min )

In this post, we share how AWS Marketing’s Technology, AI, and Analytics (TAA) team worked with Gradial to build an agentic AI solution on Amazon Bedrock for accelerating content publishing workflows.  ( 111 min )

In this post, we demonstrate two approaches to fine-tune Amazon Nova Micro for custom SQL dialect generation to deliver both cost efficiency and production ready performance.  ( 114 min )

Online retailers face a persistent challenge: shoppers struggle to determine the fit and look when ordering online, leading to increased returns and decreased purchase confidence. The cost? Lost revenue, operational overhead, and customer frustration. Meanwhile, consumers increasingly expect immersive, interactive shopping experiences that bridge the gap between online and in-store retail. Retailers implementing virtual try-on […]  ( 114 min )

In this post, you'll learn why probabilistic AI validation falls short in regulated industries and how Automated Reasoning checks use formal verification to deliver mathematically proven results. You'll also see how customers across six industries use this technology to produce formally verified, auditable AI outputs, and how to get started.  ( 111 min )

Today, we're announcing sheet tooltips in Amazon Quick Sight. Dashboard authors can now design custom tooltip layouts using free-form layout sheets. These layouts combine charts, key performance indicator (KPI) metrics, text, and other visuals into a single tooltip that renders dynamically when readers hover over data points.  ( 110 min )

In this post, you will learn how speculative decoding works and why it helps reduce cost per generated token on AWS Trainium2.  ( 111 min )

This post is cowritten by Renata Salvador Grande, Gabriel Bueno and Paulo Laurentys at Rede Mater Dei de Saúde. The growing adoption of multi-agent AI systems is redefining critical operations in healthcare. In large hospital networks, where thousands of decisions directly impact cash flow, service delivery times, and the risk of claim denials, the ability […]  ( 110 min )

In this post, we introduce the Generative AI Path-to-Value (P2V) framework, a structured approach to help you move generative AI initiatives from concept to production and sustained value creation.  ( 117 min )

We're excited to announce the launch of Amazon SageMaker JumpStart optimized deployments. SageMaker JumpStart improved deployments address the need for rich and straightforward deployment customization on SageMaker JumpStart by offering pre-defined deployment configurations, designed for specific use cases. Customers maintain the same level of visibility into the details of their proposed deployments, but now deployments are optimized for their specific use case and performance constraint.  ( 107 min )

This post explores how Amazon SageMaker HyperPod provides a comprehensive solution for inference workloads. We walk you through the platform’s key capabilities for dynamic scaling, simplified deployment, and intelligent resource management. By the end of this post, you’ll understand how to use the HyperPod automated infrastructure, cost optimization features, and performance enhancements to reduce your total cost of ownership by up to 40% while accelerating your generative AI deployments from concept to production.  ( 111 min )

In this post, we walk through how Guidesly built Jack AI on AWS using AWS Lambda, AWS Step Functions, Amazon Simple Storage Service (Amazon S3), Amazon Relational Database Service (Amazon RDS), Amazon SageMaker AI, and Amazon Bedrock to ingest trip media, enrich it with context, apply computer vision and generative AI, and publish marketing-ready content across multiple channels—securely, reliably, and at scale.  ( 116 min )

With the new Spring AI AgentCore SDK, you can build production-ready AI agents and run them on the highly scalable AgentCore Runtime. The Spring AI AgentCore SDK is an open source library that brings Amazon Bedrock AgentCore capabilities into Spring AI. In this post, we build an AI agent starting with a chat endpoint, then adding streaming responses, conversation memory, and tools for web browsing and code execution.  ( 112 min )

This post demonstrates how Lambda enables scalable, cost-effective reward functions for Amazon Nova customization. You'll learn to choose between Reinforcement Learning via Verifiable Rewards (RLVR) for objectively verifiable tasks and Reinforcement Learning via AI Feedback (RLAIF) for subjective evaluation, design multi-dimensional reward systems that help you prevent reward hacking, optimize Lambda functions for training scale, and monitor reward distributions with Amazon CloudWatch. Working code examples and deployment guidance are included to help you start experimenting.  ( 117 min )

View on sreweekly.com A message from our sponsor, Archera: AI workloads are unpredictable, which makes cloud commitments feel like a gamble. Archera insures your commitments against underutilization, so you can push coverage higher without the risk of getting stuck. If usage drops, Archera covers the downside. Commitment Release Guarantee included. Start Saving Ashby taught us […]  ( 4 min )

This post shows you how to manage FM transitions in Amazon Bedrock, so you can make sure your AI applications remain operational as models evolve. We discuss the three lifecycle states, how to plan migrations with the new extended access feature, and practical strategies to transition your applications to newer models without disruption.  ( 111 min )

Today, we're announcing AWS Agent Registry (preview) in AgentCore, a single place to discover, share, and reuse AI agents, tools, and agent skills across your enterprise.  ( 109 min )

This post walks you through three steps: starting a session and generating the Live View URL, rendering the stream in your React application, and wiring up an AI agent that drives the browser while your users watch. At the end, you will have a working sample application you can clone and run.  ( 113 min )

In this post, you will learn how to build stateful MCP servers that request user input during execution, invoke LLM sampling for dynamic content generation, and stream progress updates for long-running tasks. You will see code examples for each capability and deploy a working stateful MCP server to Amazon Bedrock AgentCore Runtime.  ( 115 min )

In this post, we'll walk you through a complete implementation of model fine-tuning in Amazon Bedrock using Amazon Nova models, demonstrating each step through an intent classifier example that achieves superior performance on a domain specific task. Throughout this guide, you'll learn to prepare high-quality training data that drives meaningful model improvements, configure hyperparameters to optimize learning without overfitting, and deploy your fine-tuned model for improved accuracy and reduced latency. We'll show you how to evaluate your results using training metrics and loss curves.  ( 119 min )

In healthcare and life sciences, AI agents help organizations process clinical data, submit regulatory filings, automate medical coding, and accelerate drug development and commercialization. However, the sensitive nature of healthcare data and regulatory requirements like Good Practice (GxP) compliance require human oversight at key decision points. This is where human-in-the-loop (HITL) constructs become essential. In this post, you will learn four practical approaches to implementing human-in-the-loop constructs using AWS services.  ( 110 min )

This post walks you through understanding audio embeddings, implementing Amazon Nova Multimodal Embeddings, and building a practical search system for your audio content. You'll learn how embeddings represent audio as vectors, explore the technical capabilities of Amazon Nova, and see hands-on code examples for indexing and querying your audio libraries. By the end, you'll have the knowledge to deploy production-ready audio search capabilities.  ( 116 min )

In this post, we explore where RFT is most effective, using the GSM8K mathematical reasoning dataset as a concrete example. We then walk through best practices for dataset preparation and reward function design, show how to monitor training progress using Amazon Bedrock metrics, and conclude with practical hyperparameter tuning guidelines informed by experiments across multiple models and use cases.  ( 119 min )

With Amazon Bedrock Projects, you can attribute inference costs to specific workloads and analyze them in AWS Cost Explorer and AWS Data Exports. In this post, you will learn how to set up Projects end-to-end, from designing a tagging strategy to analyzing costs.  ( 109 min )

This post walks through building an automated podcast generator that creates engaging conversations between two AI hosts on any topic, demonstrating the streaming capabilities of Nova Sonic, stage-aware content filtering, and real-time audio generation.  ( 112 min )

In this post, we show you how to build a natural text-to-SQL solution using Amazon Bedrock that transforms business questions into database queries and returns actionable answers.  ( 115 min )

In this post, we walk through building a custom HR onboarding agent with Quick. We show how to configure an agent that understands your organization’s processes, connects to your HR systems, and automates common tasks, such as answering new-hire questions and tracking document completion.  ( 114 min )

In this post, we walk through how we fine-tuned Qwen 2.5 7B Instruct for tool calling using RLVR. We cover dataset preparation across three distinct agent behaviors, reward function design with tiered scoring, training configuration and results interpretation, evaluation on held-out data with unseen tools, and deployment.  ( 113 min )

In this post, we show how to implement a generative AI agentic assistant that uses both semantic and text-based search using Amazon Bedrock, Amazon Bedrock AgentCore, Strands Agents and Amazon OpenSearch.  ( 115 min )

This blog post demonstrates how Windward helps enhance and accelerate alert investigation processes by combining geospatial intelligence with generative AI, enabling analysts to focus on decision-making rather than data collection.  ( 110 min )

Amazon Bedrock AgentCore Gateway provides a centralized layer for managing how AI agents connect to tools and MCP servers across your organization. In this post, we walk through how to configure AgentCore Gateway to connect to an OAuth-protected MCP server using the Authorization Code flow.  ( 114 min )

View on sreweekly.com A message from our sponsor, Depot: CI was designed for humans who context-switch while waiting. Agents don’t. They’re just blocked. Depot CEO Kyle Galbraith on how they re-imagined Depot CI to close the loop: run against local patches, rerun a single job, SSH into the runner to check reality. Per-second billing, no […]  ( 3 min )