# Expert (400) Published articles for Expert (400). This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Build an AI-powered product tagging system with Amazon SageMaker serverless model customization DevFeed: [Build an AI-powered product tagging system with Amazon SageMaker serverless model customization]() Original publisher: [Read original article]() Author: Linpo Guo Published: 2026-09-15T16:11:36Z Content type: tutorial Language: en Sources: [Artificial Intelligence]() Topics: [Artificial Intelligence](), [Amazon SageMaker AI](), [Fine-tuning](), [rlvr](), [grpo](), [Inference](), [model-deployment](), [Reinforcement learning](), [SDK](), [Serverless]() Tags: [ai](), [amazon-sagemaker](), [amazon-sagemaker-ai](), [aws](), [compute](), [cost](), [customization](), [expert-400](), [fine-tuning](), [inference](), [jobs](), [reinforcement-learning](), [rlvr](), [sdk](), [technical-how-to]() ### AI overview This walkthrough shows how to build a product tagging system by customizing Qwen3-8B with supervised fine-tuning and reinforcement learning with verifiable rewards on Amazon SageMaker serverless model customization. It then deploys the optimized model for asynchronous inference to enrich retail catalogs. ### Source excerpt Manually tagging thousands of catalog products is slow and inconsistent. This walkthrough shows how to customize Qwen3-8B with supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) on Amazon SageMaker serverless model customization, then deploy it for asynchronous inference to build a cost-efficient product tagging system. ## Operationalizing least privilege: Automate IAM remediation through your CI/CD pipeline DevFeed: [Operationalizing least privilege: Automate IAM remediation through your CI/CD pipeline]() Original publisher: [Read original article]() Author: Luis Pastor Published: 2026-09-15T15:53:51Z Content type: tutorial Language: en Sources: [AWS Security Blog]() Topics: [AWS Identity and Access Management (IAM)](), [CI/CD](), [Infrastructure as code](), [AWS CloudFormation](), [Amazon Web Services]() Tags: [aws](), [aws-cloudformation](), [aws-cloudtrail](), [aws-iam](), [aws-identity-and-access-management-iam](), [aws-organizations](), [best-practices](), [ci-cd](), [expert-400](), [iam](), [infrastructure-as-code-iac](), [least-privilege](), [pull-request](), [security](), [security-blog](), [security-identity-compliance](), [technical-how-to]() ### AI overview This article describes an automated workflow for operationalizing least privilege in AWS. It explains how AWS IAM Access Analyzer identifies unused permissions and how remediation can be routed through different paths for infrastructure-as-code-managed, manually created, and unused IAM principals. ### Source excerpt The principle of least privilege is straightforward to articulate but challenging to maintain at scale. When teams first deploy applications to AWS, they often grant broader permissions than strictly necessary; it's faster to get things working, and the plan is always to tighten permissions later. But later rarely comes. Permissions accumulate, AWS Identity and Access [...] ## Reduce inference cold starts on Amazon SageMaker HyperPod with model caching DevFeed: [Reduce inference cold starts on Amazon SageMaker HyperPod with model caching]() Original publisher: [Read original article]() Author: Kareem Syed-Mohammed Published: 2026-09-10T21:37:49Z Content type: tutorial Language: en Sources: [Artificial Intelligence]() Topics: [Caching](), [Inference](), [model-deployment](), [Large Language Model](), [autoscaling](), [Kubernetes](), [Amazon S3]() Tags: [amazon](), [amazon-s3](), [amazon-sagemaker](), [amazon-sagemaker-hyperpod](), [announcements](), [autoscaling](), [benchmark](), [caching](), [expert-400](), [inference](), [kubernetes](), [llm]() ### AI overview Amazon SageMaker HyperPod model caching preloads model weights and container images onto cluster nodes, reducing inference-pod cold starts by serving assets from local NVMe storage. ### Source excerpt Amazon SageMaker HyperPod now supports model caching for inference, which pre-loads model weights and container images onto cluster nodes so pods read from local NVMe storage instead of downloading over the network. Learn how model caching cuts cold starts from tens of minutes to seconds, how it works, and how to enable it. ## From noise to signal: Monitoring Amazon DocumentDB like a pro DevFeed: [From noise to signal: Monitoring Amazon DocumentDB like a pro]() Original publisher: [Read original article]() Author: Deepak Deepesh Published: 2026-09-09T15:23:20Z Content type: tutorial Language: en Sources: [AWS Database Blog]() Topics: [Amazon DocumentDB](), [site-reliability-engineering](), [Amazon CloudWatch Logs](), [Database]() Tags: [amazon](), [amazon-cloudwatch](), [amazon-cloudwatch-logs](), [amazon-documentdb](), [best-practices](), [database](), [devops](), [expert-400](), [health](), [how-to](), [logs](), [metrics](), [monitoring](), [on-call](), [operations](), [performance](), [production]() ### AI overview A tutorial on monitoring production Amazon DocumentDB clusters with tiered alerts, CloudWatch metrics, Performance Insights, profiler logs, slow-query diagnosis, and garbage-collection health checks. ### Source excerpt Learn how to build a tiered alerting strategy for Amazon DocumentDB by organizing CloudWatch metrics into Critical, Warning, and Advisory tiers, diagnosing slow queries through three complementary lenses, and monitoring garbage collection health before it becomes a cluster-wide incident. ## Extend Amazon Bedrock Guardrails to Tool Interactions Using the Strands Agents SDK DevFeed: [Extend Amazon Bedrock Guardrails to Tool Interactions Using the Strands Agents SDK]() Original publisher: [Read original article]() Author: Stephan Traub Published: 2026-08-27T16:20:05Z Content type: tutorial Language: en Sources: [AWS Security Blog]() Topics: [AI Bots](), [AWS IAM]() Tags: [ai-agents](), [amazon-bedrock](), [amazon-bedrock-guardrails](), [artificial-intelligence](), [aws-identity-and-access-management-iam](), [expert-400](), [generative-ai](), [model-context-protocol](), [security-blog](), [security-identity-compliance](), [strands-agents](), [tools](), [validation]() ### AI overview A tutorial on extending Amazon Bedrock Guardrails beyond model prompts and responses to validate AI-agent tool interactions with Strands Agents SDK lifecycle hooks. ### Source excerpt If you're running AI agents in production, Amazon Bedrock Guardrails protects the model boundary. But your agents also invoke tools, fetch external data, and communicate with other systems. That data flows outside the model boundary, where model-level guardrails can't reach. You can extend guardrail coverage to those interactions using three validation checkpoints built with the [...]