Fine-tuning for domain-specific tasks means improving performance in one area without degrading the model’s general capabilities, and getting that balance right is harder than it looks. This post walks through how to navigate that balance, from selecting the right customization strategy for your data and task, to configuring the training parameters that most influence outcomes, like learning rate, batch size, and checkpointing. We also cover the common mistakes that lead to wasted training runs and how to catch them early, so you can improve domain performance without degrading general capabilities or burning through compute on avoidable failures. By the end, you will know how to improve domain performance without degrading general capabilities and how to avoid the expensive failures that come from getting the balance wrong.  ( 122 min )

In this post, we'll walk through implementing object detection with Amazon Nova 2 Lite. You'll learn how to deploy an object detection application using Amazon Bedrock, AWS Lambda, and Amazon API Gateway. You'll also learn how to craft effective prompts, process structured JSON output, and visualize results. We explore practical applications across manufacturing, agriculture, and logistics.  ( 112 min )

This post walks through how Baz built their Spec Review agent using Amazon Bedrock and Amazon Bedrock AgentCore. We'll cover the architecture decisions, implementation details, and the business outcomes they achieved by leveraging these AWS services to automate their code review process  ( 110 min )

This post demonstrates how to implement Open Authorization (OAuth) Code flow as an inbound authorization mechanism for MCP servers hosted on Amazon Bedrock AgentCore Gateway. By the end of this guide, you will have a production-ready setup where each AI assistant request is authenticated with a valid user identity token issued from your organization’s identity provider.  ( 115 min )

Today, we’re excited to announce the ability to reference a secret in AWS Secrets Manager for AgentCore Identity, so you can reference your own preconfigured secret from Secrets Manager and retain full control over how it is managed. With this ability, you can extend your organization’s existing secrets governance processes to AgentCore. You can provide an existing, preconfigured AWS Secrets Manager secret to use with your credential provider resources. You retain full control over its encryption configuration, rotation, replication, tags, and resource policies, just as you would manage other secrets in Secrets Manager. You can also choose a secret from another AWS account within the same AWS Region, though cross-Region secret sharing isn’t supported. This also supports secrets brought in through AWS Secrets Manager external connectors, enabling integration with third-party secret managers.  ( 111 min )

In this post, we walk through how to use Amazon Quick Research to integrate biomedical data sources for rare cancer research. The walkthrough uses pediatric sarcoma as the research domain and draws on publicly available datasets from PubMed and other open biomedical repositories. It covers the end-to-end workflow: defining a research objective, configuring data sources, reviewing the AI-generated research plan, running the investigation, and iterating on results using the revision and versioning system.  ( 113 min )

GPT-5.5, GPT-5.4, and Codex are now generally available on Amazon Bedrock. Deploy them in production applications and agents today, on Bedrock’s high performance inference engine.  ( 109 min )

While deploying Model Context Protocol (MCP) servers in production, enterprises need fine-grained access control across servers, observability into which teams use which tools, security guarantees against data exfiltration, and centralized credential management, all at scale. Amazon Bedrock AgentCore Gateway sits between MCP servers and the clients that consume them, centralizing credential management, observability, and secure […]  ( 116 min )

In this post, we use a lakehouse data agent to demonstrate how you can use Policy for deterministic access control and Lambda interceptors for dynamic validation. We then show how to combine Lambda interceptors and Policy to implement a geography-based access control which requires both dynamic validation and deterministic access control.  ( 119 min )

In this post, we address several key risks that surface when designing an agentic payment system, and how to address them with the capabilities of AgentCore payments.  ( 114 min )

When you build agentic AI solutions, you face unique operational challenges. Agents make unpredictable decisions, costs spiral unexpectedly, and debugging non-deterministic failures seems impossible. Agentic AI applications don't just execute predetermined workflows. They reason, adapt, and make autonomous decisions, and DevOps practices need to be adapted. That's where AgentOps comes in, the operational discipline for deploying, managing, and continuously improving AI agents in production.  ( 123 min )

If you’re iterating on deploying large language models (LLMs) on AWS GPU instances, you’ve probably noticed the larger the model to be loaded into GPU High Bandwidth Memory (HBM), the longer the painful wait until the GPUs are ready for inference. As models grow to hundreds of billions of parameters and GPU environments grow ever […]  ( 119 min )

In this post, we walk through a practical implementation using KDB-X MCP server integration with Amazon Quick, demonstrating how traders and analysts can ask questions using conversational language and receive actionable insights from datasets. You can apply this same integration pattern across various domains, from financial market analysis to IoT sensor monitoring to DevOps performance dashboards, where you need to simplify access to time series insights.  ( 115 min )

View on sreweekly.com A message from our sponsor, BigPanda: What if you could predict which changes will cause incidents? BigPanda analyzes every change, including ones marked safe, to surface the real risk and impact before deployment. Next time, routine changes don’t become your next P1. See BigPanda for SREs The Problem with AI-Generated Post-Incident Reviews […]  ( 4 min )

This post demonstrates a comprehensive observability solution using Amazon Managed Grafana dashboards that provides a holistic view of both quality and quantity for LLMs served on Amazon SageMaker AI endpoints with inference components.  ( 113 min )

Azercell Telecom LLC, Azerbaijan's leading telecommunications provider, wanted to build an Azerbaijani large language model (LLM) on Amazon SageMaker AI for telecom use cases and a customer-facing chatbot. The challenge: adapting foundation models (FMs) to a morphologically rich language with limited training data and no existing blueprint for efficient LLM training in Azerbaijani. In a six-week collaboration, Azercell worked with the AWS Generative AI Innovation Center to establish a production-ready framework on Amazon SageMaker AI.  ( 115 min )

In this post, you learn how to build a custom portal with embedded SageMaker AI MLflow Apps UI. You walk through the architecture pattern behind a React front end paired with a Flask reverse proxy that handles AWS Signature Version 4 (SigV4) authentication, deploy the entire stack through the AWS Cloud Development Kit (AWS CDK), validate the deployment, and review security considerations and cleanup procedures.  ( 114 min )

In this post, we demonstrate how to build a secure Flask-based MLflow proxy service that provides HTTPS access to Amazon SageMaker MLflow without requiring the MLflow SDK. This solution is for organizations undergoing cloud transformation who want to preserve their existing ML workflows while adopting cloud-native services.  ( 112 min )

This post combines learnings from LangChain’s work on evaluating deep agents and Anthropic’s guide to demystifying evals for AI agents into a practical guide. In this post, you will learn how to: 1) apply five evaluation patterns for deep agents, 2) build offline evaluations using pytest and LangSmith, and 3) configure online monitoring for production. The walkthrough uses a text-to-SQL deep agent with Amazon Bedrock for the full development to production lifecycle.  ( 119 min )

Agent evaluation is most powerful when you combine fast-moving online signals with stable offline baselines. To understand whether your agent is truly improving over time, you need a fixed benchmark alongside your changing real-world traffic. Managing test cases for evaluation baselines as a dataset in Amazon Bedrock AgentCore brings the discipline of versioned test fixtures […]  ( 116 min )

This post covers Opus 4.8's improvements and practical guidance for AI engineers integrating the model into agentic systems and production inference workloads on Amazon Bedrock.  ( 109 min )

This post demonstrates that integration in action by automating one of the most labor-intensive workflows in financial services: anti-money laundering (AML) alert triage. You will build a triage workflow using Amazon Quick Flows and Snowflake Cortex, connected through the Amazon Quick Model Context Protocol (MCP) integration. In our testing environment, automated workflows built using Amazon Quick reduced alert investigation time from 30-90 minutes to under 5 minutes. Actual results may vary based on alert complexity and data volume.  ( 119 min )

In this post, we explore how Amazon Bedrock Data Automation can accurately extract information from four common types of financial documents: bank statements, W-2 forms, 1099-B tax forms, and vendor contracts. We highlight the complexity in the documents, detail the custom extraction created in Amazon Bedrock Data Automation, and describe the outcomes of the extraction process.  ( 112 min )

In this post, we share how the AWS Generative AI Innovation Center (GenAIIC) collaborated with Works Human Intelligence (WHI) to build two AI agents using Amazon Bedrock AgentCore. We discuss the challenges encountered and the solutions that reduced costs by up to 97% while improving operational efficiency.  ( 111 min )

In this post, we show you how Verizon Connect built and scaled an agentic AI solution to transform overwhelming fleet data into clear, actionable insights for 100,000 users daily. We walk you through the architectural decisions, implementation challenges, and measurable results that can guide your own data-to-insights transformation.  ( 114 min )

In this post, we share how we built NarrateAI using Amazon Bedrock AgentCore to deliver business intelligence at scale for the AWS SMGS (Sales, Marketing and Global Services) organization. You will learn about: the two-layer architecture that separates batch processing from real-time interaction, the specialized AI agents that power intelligent routing and validation, key engineering patterns for production deployment, and how to build similar solutions with AWS services.  ( 115 min )

As agent adoption scaled, we saw a common pattern emerge across enterprises, including our own sales organization: specialized agents deliver value, but without orchestration, users carry the cognitive load of choosing between them. At AWS Sales, this meant more than 20 domain-specific agents deployed across the global organization, with representatives context-switching between systems instead of […]  ( 118 min )

Amazon Bedrock AgentCore payments is now available in preview, it provides instant payments to paid external services with no manual billing setup per provider, stablecoin support for cost-effective microtransactions that make sub-cent transactions economically viable, and configurable spending guardrails that give you fine-grained control over agent budgets and transaction limits. In this post, we walk you through a technical deep dive of AgentCore payments.  ( 118 min )

In this post, we provide a solution to build highly scalable, serverless multi-agent generative AI systems on AWS using LangGraph Agents as orchestrators integrated with Amazon Bedrock AgentCore Memory and Amazon Bedrock AgentCore Observability.  ( 111 min )

In this post you'll learn how to build a multi-agent campaign review system that demonstrates parallel reasoning, context persistence, and traceable execution paths using an integrated architecture that combines NVIDIA NIM for GPU-accelerated inference. Amazon Bedrock AgentCore provides managed runtime, shared memory and built-in observability and Strands Agents provide serverless multi-agent orchestration. This approach supports performance, scalability, and operational insight in production environments. While the example focuses on marketing content review, the same pattern applies to digital assistants, review automation, and retrieval-augmented generation pipelines.  ( 111 min )

In this post, we demonstrate the capabilities of AgentWatch through practical implementation. You will see how the solution performs infrastructure checks every 15 minutes, summarizing CloudWatch metrics, logs, and alarms across multiple AWS accounts. The agent delivers actionable reports directly to Slack and responds to natural language queries about your infrastructure state. Throughout, we explore three human-in-the-loop patterns that maintain appropriate oversight while maximizing automation.  ( 115 min )

Building an AI app shouldn’t require a PhD in machine learning (ML) or months of wrestling with complex architectures. Yet that’s exactly what happens when you try to orchestrate multiple API calls, manage conversation state, and create agents that can reason on their own. I’ve seen straightforward AI ideas balloon into sprawling projects that demand […]  ( 114 min )

When hundreds to thousands of users are onboarded to an enterprise AI platform, business leaders and platform owners need visibility into who is using the platform, whether users are satisfied with the answers they receive, and which capabilities are driving the most engagement. Without a centralized observability solution, this data is scattered across multiple AWS […]  ( 111 min )

In this post, we explore how the Amazon Quick document and visualization creation capabilities work, what you can build with them, and how professionals across roles are using them to reclaim hours of their workweek. From technical execution to strategic judgment Most professional roles carry an unspoken assumption that a significant portion of your time […]  ( 113 min )

View on sreweekly.com A message from our sponsor, BigPanda: When a P1 fires, scope, impact, and cause should be instant. Instead you’re 10 minutes in, pinging people across tools and teams to understand what’s happening. BigPanda surfaces the full picture the moment an incident starts so you fix, not hunt. Reduce incident toil When AI […]  ( 4 min )

In this post, you will learn what Nova Act offers, how HIPAA eligibility applies to agentic AI, and how to get started.  ( 109 min )

Many healthcare organizations report that traditional worklist systems rely on rigid rules that ignore critical context, radiologist specialization, current workload, fatigue levels, and case complexity. This creates a persistent challenge: radiologists cherry-pick easier, higher-value cases while avoiding complex studies, leading to diagnostic delays and increased costs. Research across 62 hospitals analyzing 2.2 million studies found […]  ( 117 min )

This post shows you how to use Amazon Bedrock AgentCore Runtime with Model Context Protocol (MCP) support to connect Amazon Quick with AWS services through the AWS API MCP Server, creating a conversational AI assistant that translates natural language into AWS Command Line Interface (AWS CLI) commands, without the need to switch between tools during critical moments.  ( 117 min )

This post explores design considerations for architecting multi-tenant agentic applications and the framework needed to address SaaS architecture challenges with Amazon Bedrock AgentCore.  ( 119 min )

In this post, you will learn how to implement Recursive Language Models (RLM) using Amazon Bedrock AgentCore Code Interpreter and the Strands Agents SDK. By the end, you will know how to process documents of varying lengths, with no upper bound on context size, use Bedrock AgentCore Code Interpreter as persistent working memory for iterative document analysis, and orchestrate sub-large language model (sub-LLM) calls from within a sandboxed Python environment to analyze specific document sections.  ( 116 min )

In this post, we show you how OPLOG developed three AI agents using the Strands Agents SDK, deployed them to Amazon Bedrock AgentCore, and integrated Amazon Bedrock with Anthropic’s Claude Sonnet and Amazon Bedrock Knowledge Bases for Retrieval Augmented Generation (RAG).  ( 115 min )

In this post, we demonstrate how to build an AI-powered recruitment assistant using Amazon Bedrock that brings efficiencies to candidate evaluation, generates personalized interview questions, and provides data-driven insights for human hiring decisions. This post presents a reference architecture for learning purposes — not a production-ready solution. Amazon Bedrock and the AWS services used here are general-purpose tools that customers can combine to support a wide variety of use cases, including recruitment workflows. The architecture demonstrates one possible approach; customers should adapt it to their specific requirements.  ( 117 min )

This solution combines the power of Amazon Bedrock AgentCore, Strands Agents, and Amazon Quick transforms to deliver a secure, scalable, and intelligent system for building and operating AI agents while transforming data into actionable business insights.  ( 117 min )

Today, Amazon SageMaker AI introduces OpenAI-compatible API support for real-time inference endpoints. If you use the OpenAI SDK, LangChain, or Strands Agents, you can now invoke models on SageMaker AI by changing only your endpoint URL. You don’t need a custom client, a SigV4 wrapper, or code rewrites. Overview With this launch, SageMaker AI endpoints […]  ( 115 min )

If you’re building visual shopping, image or document understanding, or chart analysis, you need a way to verify whether your model’s response is actually grounded in the source image. A text-only evaluator cannot tell you whether a caption faithfully describes an image, whether an extracted invoice total matches the document, or whether a screen summary […]  ( 114 min )

Voice agents, live captioning, contact center analytics, and accessibility tools all depend on real-time speech-to-text, where your application streams audio in and receives transcription back simultaneously over a single persistent connection. Traditional request-response inference falls short here because transcription cannot begin until the entire audio recording has been received, adding latency that breaks the real-time […]  ( 115 min )

In this post, you’ll learn how to use Amazon Nova Sonic, Amazon Bedrock AgentCore, and Strands BidiAgent to build scalable, maintainable voice agents that handle these challenges efficiently, resulting in more responsive and intelligent customer interactions. We’ll explore three popular architectural patterns for voice agents, highlighting their trade-offs and best practices for minimizing latency.  ( 114 min )

In this post, we demonstrate how you can extend the conversational memory of Kiro CLI by implementing a custom Model Context Protocol (MCP) server that integrates with Amazon Bedrock AgentCore Memory. You can use Kiro CLI to interact with AI agents of Kiro directly from your terminal. Amazon Bedrock AgentCore Memory is a fully managed service that allows AI agents to retain information from past interactions, creating more intelligent and context-aware conversations. By implementing a custom MCP server, you can provide Kiro CLI with tools to store and retrieve conversation context, monitor memory usage, and manage the underlying Bedrock Agent Core Memory infrastructure.  ( 111 min )

Today, we’re announcing three new capabilities available in SageMaker Python SDK v3.8.0. In this post, we walk through each capability with code examples you can use to get started. For complete end-to-end walkthroughs, see the accompanying notebooks for Lake Formation governance and Iceberg table properties in the SageMaker Python SDK repository.  ( 114 min )

In this post, we show three ways to implement Programmatic tool calling (PTC) on Amazon Bedrock: a self-hosted Docker sandbox on ECS for maximum control, a managed solution using Amazon Bedrock AgentCore Code Interpreter, and an Anthropic SDK-compatible path through a proxy for teams that prefer that developer experience.  ( 118 min )

In this post, you learn how to prompt Amazon Nova 2 Lite for content moderation using structured and free-form approaches, grounded in the MLCommons AILuminate Assessment Standard. The prompting techniques use the AILuminate taxonomy as an example, but they work equally well with your own custom moderation policy. You can swap in your own category definitions and the prompt structure stays the same. We also benchmark the content moderation capabilities of Amazon Nova 2 Lite against several foundation models (FMs) on three public datasets.  ( 117 min )

In this post, we share how Aderant used the AI-powered capabilities of Amazon Quick to unify search across six vendor systems and automate documentation workflows, achieving 90 percent faster search times and 75 percent documentation acceleration, and how others can apply these approaches to their operations.  ( 111 min )

In this post, you will learn how to set up the Confluence Cloud integration with Quick. This includes creating a knowledge base for semantic search, setting up Actions to query and manage Confluence pages, and organizing resources in Quick Spaces. Quick integrates with your current enterprise technology stack, from internal knowledge repositories and corporate intranets to business-critical applications and AWS data services.  ( 117 min )

In this post, you will implement four Lambda-based custom code evaluators for a financial market-intelligence agent, register each with AgentCore, and run them in on-demand and online modes. You will also see how to combine custom code-based evaluators with built-in evaluators and how to call other AWS services for grounded fact-checking, PII detection, and real-time alerting.  ( 117 min )

View on sreweekly.com A message from our sponsor, BigPanda: No single team sees the full incident anymore. Today’s P1s break across services, teams, and infrastructure. Instead of chasing dashboards, waiting on tribal knowledge, or piecing together signals from siloed systems, BigPanda surfaces the complete picture to pinpoint root cause faster. See BigPanda for SREs Why […]  ( 4 min )

In this post, we walk through how to configure document-level ACLs for your S3 knowledge base in Amazon Quick. You will learn how to set up and verify an ACL configuration that enforces document-level permissions across chat and automated workflows.  ( 119 min )

In this post, you will learn how to implement Assisted NLU effectively. You will learn how to improve your bot design with effective intent and slot descriptions, validate your implementation using Test Workbench, and plan your transition from traditional NLU to Assisted NLU for both new and existing bots.  ( 117 min )

In this post, you learn how to combine Stream's Vision Agents open-source framework with Amazon Bedrock and Amazon Nova 2 Sonic to build real-time voice agents that can be production-ready in minutes. You'll learn how the integration works under the hood, walk through code examples, and explore advanced capabilities like function calling, automatic reconnection, and multilingual voice support.  ( 117 min )

Today, we're announcing cross-account Athena access for Amazon Quick. With this feature, customers can query Athena data in other AWS accounts using AWS Identity and Access Management (IAM) role chaining, with query costs billed to the account where the data resides.  ( 117 min )

In this post, you will configure Chrome enterprise policies to restrict a browser agent to a specific website, observe the policy enforcement through session recording, and demonstrate custom root CA certificates using a public test site. The walkthrough produces a working solution that researches Amazon Bedrock AgentCore documentation while operating under enterprise browser restrictions.  ( 116 min )

This post demonstrates how to build a documentation extraction and model fine-tuning pipeline that addresses challenges when processing the complex financial documents. By combining Pulse AI's advanced document understanding capabilities with the powerful AI services of Amazon Bedrock, organizations can achieve enterprise-grade accuracy and extract contextually relevant financial insights at scale.  ( 118 min )

Building end-to-end live streaming applications with real-time voice interaction presents several challenges. This post introduces a solution based on Amazon Nova 2 Sonic (Nova Sonic) and Amazon Kinesis Video Streams WebRTC (WebRTC) that addresses these challenges. In this post, we’ll walk through the solution architecture, implementation patterns, and two real-world scenario examples.  ( 112 min )

The Cisco and AWS partnership addresses three challenges enterprises face when scaling AI agents: visibility gaps, security bottlenecks, and compliance risks. In this post, we explore how you can overcome AI security challenges through automated scanning and unified governance.  ( 112 min )

In this post, we demonstrate how to build a secure, complete LLM fine-tuning workflow that integrates Unity Catalog with Amazon SageMaker AI using Amazon EMR Serverless for preprocessing. The solution shows how to securely access governed data, maintain lineage across services, fine-tune the Ministral-3-3B-Instruct model, and register trained artifacts back into Unity Catalog. With this approach, you can continue using your existing services while preserving central governance, tracking data lineage without compromising security or compliance requirements.  ( 116 min )

In this post, we demonstrate how Amazon FinTech teams are using Amazon Bedrock and other AWS services to build a scalable AI application to transform how regulatory inquiries are handled. Each team using this solution creates and maintains its own dedicated knowledge base, populated with that team's specific documents and reference materials.  ( 114 min )

In this post, we'll show you how our multi-document discovery feature solves this problem. It serves as an automated pre-processing step, analyzing unknown documents, clustering them by type, and generating schemas ready for the IDP Accelerator. You'll learn how the new capability uses visual embeddings for automatic clustering and agents for schema generation. We'll also walk you through running the solution on your own document collections.  ( 113 min )

In this post, we show you how to set up FLOPs tracking during LLM fine-tuning using the open source Fine-Tuning FLOPs Meter toolkit on Amazon SageMaker AI. You learn how to determine your compliance status with a single configuration flag and generate audit-ready documentation.  ( 115 min )

Milo is five today, which he’s mostly celebrating by snoozing on the office sofa behind me. He’s nearing the end of his fourth (modified) CHOP protocol, with just over 4 weeks and 3 more vet visits to go. Since going into remission at the start of the year things have proceeded mostly uneventfully, which is […]  ( 13 min )

Milo is five today, which he’s mostly celebrating by snoozing on the office sofa behind me. He’s nearing the end of his fourth (modified) CHOP protocol, with just over 4 weeks and 3 more vet visits to go. Since going into remission at the start of the year things have proceeded mostly uneventfully, which is […]  ( 13 min )

In this post, you will learn how to set up the Exa integration in Strands Agents, understand the two core tools it exposes, and walk through real-world use cases that show how agents use web search to complete multi-step tasks.  ( 117 min )

Today, we're excited to announce the general availability of Claude Platform on AWS. Claude Platform on AWS is a new service that gives customers direct access to Anthropic's native Claude Platform experience through their AWS account, with no separate credentials, contracts, or billing relationships required. AWS is the first cloud provider to offer access to the native Claude Platform experience. In this post, we explore how Claude Platform on AWS works and how you can start using it today.  ( 110 min )

In this post, we build a multimodal retrieval system for aerospace manufacturing documents using Amazon Nova Multimodal Embeddings on Amazon Bedrock and Amazon S3 Vectors. We evaluate the system on 26 manufacturing queries and compare generation quality between a text-only pipeline and the multimodal pipeline.  ( 115 min )

In this post, we dive deep into the architecture and techniques we used to improve Miro’s bug routing, achieving six times fewer team reassignments and five times shorter time-to-resolution powered by Amazon Bedrock.  ( 115 min )

Amazon Quick helps turn your large enterprise data into fast and accurate AI-powered decisions. In this post, you will learn about five new capabilities of Amazon Quick that accelerate how data professionals deliver trusted AI-powered insights at enterprise scale.  ( 114 min )

View on sreweekly.com A message from our sponsor, incident.io: Paging is just 10% of your incident workflow. incident.io’s 4-step framework turns migration into a forcing function for the other 90%: cut alert noise, fix service ownership, and build the on-call program your team actually deserves. Not all index scans are equal: How we cut query […]  ( 4 min )

In this post, we'll explore how we built a proof-of-concept that converts natural language queries into executable seismic workflows while providing a question-answering capability for Halliburton's Seismic Engine tools and documentation. We'll cover the technical details of the solution, share evaluation results showing workflow acceleration of up to 95%, and discuss key learnings that can help other organizations enhance their complex technical workflows with generative AI.  ( 112 min )

In this post, you will learn how to secure reserved GPU capacity for short-term workloads using Amazon Elastic Compute Cloud (Amazon EC2) Capacity Blocks for ML and Amazon SageMaker training plans. These solutions can address GPU availability challenges when you need short-term capacity for load testing, model validation, time-bound workshops, or preparing inference capacity ahead of a release.  ( 113 min )

In this post, you will learn how to implement reinforcement learning with verifiable rewards (RLVR) to introduce verification and transparency into reward signals to improve training performance. This approach works best when outputs can be objectively verified for correctness, such as in mathematical reasoning, code generation, or symbolic manipulation tasks. You will also learn how to layer techniques like Group Relative Policy Optimization (GRPO) and few-shot examples to further improve results. You’ll use the GSM8K dataset (Grade School Math 8K: a collection of grade school math problems) to improve math problem solving accuracy, but the techniques used here can be adapted to a wide variety of other use cases.  ( 117 min )

Today, we're announcing a preview of Amazon Bedrock AgentCore Payments, a new set of features in Amazon Bedrock AgentCore that enables AI agents to instantly access and pay for what they use. AgentCore Payments was developed in partnership with Coinbase and Stripe.  ( 111 min )

Tomofun, the Taiwan-headquartered pet-tech startup behind the Furbo Pet Camera, is redefining how pet owners interact with their pets remotely. To reduce costs and maintain accuracy, Tomofun turned to EC2 Inf2 instances powered by AWS Inferentia2, the Amazon purpose-built AI chips. In this post, we walk through the following sections in detail.  ( 111 min )

Hapag-Lloyd's Digital Customer Experience and Engineering team, distributed between Hamburg and Gdańsk, drives digital innovation by developing and maintaining customer-facing web and mobile products. In this post, we walk you through our generative AI–powered feedback analysis solution built using Amazon Bedrock, Elasticsearch, and open-source frameworks like LangChain and LangGraph  ( 112 min )

Today, we’re excited to announce that Amazon SageMaker AI MLflow Apps now support MLflow version 3.10, bringing enhanced capabilities for generative AI development and streamlined experiment tracking to your generative AI workflows. Building on the foundations established with Amazon SageMaker AI MLflow Apps, this latest version introduces powerful new features for observability, evaluation, and generative […]  ( 108 min )

We’re announcing OS Level Actions for AgentCore Browser. This new capability unblocks these scenarios by exposing direct OS control through the InvokeBrowser API, so agents can interact with content visible on the screen, not only what's accessible through the browser's web layer. By combining full-desktop screenshots with mouse and keyboard control at the OS level, agents can observe native UI, reason about it, and act on it within the same session. This post walks through how OS Level Actions work, what actions are supported, and how to get started.  ( 112 min )

AI agents in production require secure access to external services. Amazon Bedrock AgentCore Identity, available as a standalone service, secures how your AI agents access external services whether they run on compute platforms like Amazon ECS, Amazon EKS, AWS Lambda, or on-premises. This post implements Authorization Code Grant (3-legged OAuth) on Amazon ECS with secure session binding and scoped tokens.  ( 115 min )

In this post, you will learn how you can use Amazon Nova Foundation Models in Amazon Bedrock to apply generative AI techniques for both business protection and enhancement. You can identify obvious and disguised attempts at direct contact while gaining valuable insights into customer sentiment and service improvement opportunities.  ( 115 min )