# AWS Architecture Blog Just another Amazon Web Services site This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## From zero-shot forecast to purchase order with Amazon Bedrock AgentCore DevFeed: [From zero-shot forecast to purchase order with Amazon Bedrock AgentCore]() Original publisher: [Read original article]() Author: Hyunsoo Kim, Ph.D. Published: 2026-09-11T14:08:01Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [AI Bots](), [Training AI Models](), [SDKs]() Tags: [advanced-300](), [agents](), [amazon-bedrock](), [amazon-bedrock-agentcore](), [automation](), [best-practices](), [orchestration](), [strands-agents](), [time-series](), [training](), [zero-shot]() ### AI overview An architecture article on using Amazon Chronos2 zero-shot forecasting and Bedrock AgentCore multi-agent orchestration to turn demand forecasts into validated purchase orders without per-product model training. ### Source excerpt Combine zero-shot forecasting with Amazon Chronos2 and multi-agent orchestration on Amazon Bedrock AgentCore to turn demand forecasts into validated purchase orders. No per-product model training, with business rules, auditability, and cost that scales to zero. ## Building resilient real-time streaming workers with Amazon DynamoDB leases DevFeed: [Building resilient real-time streaming workers with Amazon DynamoDB leases]() Original publisher: [Read original article]() Author: Siddhesh Tiwari Published: 2026-09-10T16:14:22Z Content type: tutorial Language: en Sources: [AWS Architecture Blog]() Topics: [WebSocket](), [Amazon EC2](), [Amazon Elastic Kubernetes Service]() Tags: [advanced-300](), [amazon-dynamodb](), [amazon-ec2](), [amazon-eks](), [amazon-elastic-container-service](), [aws-fargate](), [how-to](), [real-time](), [streaming](), [technical-how-to](), [workers]() ### AI overview A tutorial for building resilient real-time WebSocket workers with Amazon DynamoDB leases. It covers conditional-write ownership, orphan reconciliation for automatic failover, and graceful shutdown to reduce deployment downtime on Amazon ECS and AWS Fargate. ### Source excerpt Real-time streaming workers that hold hundreds of persistent WebSocket connections lose data when a worker fails. Learn how to build a WebSocket fleet management system on Amazon ECS and AWS Fargate that uses Amazon DynamoDB conditional writes as a distributed lease to track ownership, fail over automatically, and deploy with low downtime. ## Testing application resilience with Amazon SQS and AWS Fault Injection Service DevFeed: [Testing application resilience with Amazon SQS and AWS Fault Injection Service]() Original publisher: [Read original article]() Author: Richard Whitworth Published: 2026-09-09T21:33:59Z Content type: tutorial Language: en Sources: [AWS Architecture Blog]() Topics: [Amazon Simple Queue Service (SQS)](), [AWS Fault Injection Service (FIS)](), [Chaos Engineering](), [AWS IAM](), [AWS Identity and Access Management (IAM)]() Tags: [advanced-300](), [amazon-cloudwatch](), [amazon-simple-queue-service-sqs](), [amazon-sqs](), [automation](), [aws](), [aws-fault-injection-service-fis](), [experiments](), [how-to](), [iam](), [observability](), [resilience](), [technical-how-to](), [testing]() ### AI overview A tutorial on testing application resilience when Amazon SQS data-plane operations fail. It uses AWS Fault Injection Service and Systems Manager Automation to progressively deny queue access, evaluate recovery and observability with CloudWatch metrics, and avoid IAM deny-policy lockouts. ### Source excerpt Learn how to use AWS Fault Injection Service and AWS Systems Manager Automation to run progressive chaos experiments against Amazon SQS queues. Validate that your retry logic, circuit breakers, and dead-letter queues actually work under failure before a real outage hits production. ## Validating multi-Region DR for Terraform Enterprise with AWS FIS DevFeed: [Validating multi-Region DR for Terraform Enterprise with AWS FIS]() Original publisher: [Read original article]() Author: Frenil Randeria Published: 2026-09-09T21:05:02Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [Terraform](), [AWS Fault Injection Service (FIS)](), [Chaos Engineering](), [Amazon S3](), [Amazon EC2](), [Databases]() Tags: [advanced-300](), [amazon-aurora](), [amazon-ec2](), [amazon-s3](), [aws](), [aws-fault-injection-service-fis](), [disaster-recovery](), [postgresql](), [technical-how-to](), [terraform](), [validation]() ### AI overview This article explains how to validate customer-operated multi-Region disaster recovery for Terraform Enterprise on AWS using three-phase AWS FIS experiments. It covers failover and failback testing, hidden dependency discovery, and reported recovery times of 12-14 minutes. ### Source excerpt Learn how AWS, HashiCorp, and Athenahealth designed and chaos-tested a multi-Region disaster recovery strategy for Terraform Enterprise on AWS. This post walks through three-phase AWS Fault Injection Service experiments across Amazon EC2, Aurora, and Amazon S3, the 12-14 minute recovery times achieved, and the state file dependency pitfall to avoid. ## Hybrid cloud orchestration: Modernizing on-premises infrastructure management with AWS DevFeed: [Hybrid cloud orchestration: Modernizing on-premises infrastructure management with AWS]() Original publisher: [Read original article]() Author: Sandeep Singh Published: 2026-09-01T14:01:10Z Content type: tutorial Language: en Sources: [AWS Architecture Blog]() Topics: [Orchestration](), [Kubernetes](), [Amazon EKS](), [AWS Lambda](), [Server](), [Hardware]() Tags: [amazon-dynamodb](), [amazon-eks](), [aws](), [aws-lambda](), [aws-step-functions](), [data-centers](), [deployment](), [event-driven](), [hardware](), [kubernetes](), [observability](), [orchestration](), [server](), [serverless](), [thought-leadership]() ### AI overview Tutorial on designing an AWS-based hybrid cloud orchestration system for centralized lifecycle management of distributed on-premises servers and EKS Anywhere clusters. ### Source excerpt Learn how to build a hybrid cloud orchestration solution that manages distributed on-premises infrastructure at scale using AWS serverless technologies and Amazon EKS Anywhere. Part 1 covers the core event-driven architecture patterns for automating server lifecycle and cluster management across hundreds of sites. ## MCP went stateless: Is your AWS MCP server deployment well-architected? DevFeed: [MCP went stateless: Is your AWS MCP server deployment well-architected?]() Original publisher: [Read original article]() Author: Anand Komandooru Published: 2026-09-01T13:09:19Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [Model Context Protocol](), [Deployment](), [schema-evolution](), [Amazon Bedrock]() Tags: [amazon-bedrock](), [announcements](), [aws](), [best-practices](), [deployment](), [mcp](), [mcp-server](), [observability]() ### AI overview The article explains MCP's move to a stateless core and how it simplifies AWS MCP server deployments by removing the need for sticky sessions and shared session stores. It maps the MCP 2026-07-28 specification to AWS Well-Architected Agentic AI Lens practices and recommends migration. ### Source excerpt On July 28, 2026, MCP made its protocol core stateless, removing the initialize handshake and session header. This post maps the MCP 2026-07-28 specification to the AWS Well-Architected Agentic AI Lens, pillar by pillar, and shows why the stateless design lets you delete the sticky sessions and session stores your MCP servers needed on AWS. ## Gallup scales real-time coaching for thousands with Amazon Bedrock DevFeed: [Gallup scales real-time coaching for thousands with Amazon Bedrock]() Original publisher: [Read original article]() Author: Tamil Sambasivam Published: 2026-08-26T17:36:23Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [AI Chat](), [Language models]() Tags: [amazon-bedrock](), [amazon-bedrock-knowledge-bases](), [anthropic](), [aws](), [claude](), [customer-solutions](), [generative-ai](), [retrieval-augmented-generation-rag](), [safety]() ### AI overview Gallup built a generative AI coaching assistant with Amazon Bedrock and Anthropic Claude models to provide leaders with real-time, personalized workplace guidance in Gallup Access. ### Source excerpt Gallup transformed 90 years of workplace science into Gallup AI, a generative AI assistant powered by Amazon Bedrock that delivers real-time, personalized coaching to leaders directly within the Gallup Access application. ## Closing the AI agent trust gap with graduated autonomy DevFeed: [Closing the AI agent trust gap with graduated autonomy]() Original publisher: [Read original article]() Author: Dev Arora Published: 2026-08-26T17:33:03Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [Artificial Intelligence](), [AI Agent](), [Authorization](), [Amazon Bedrock](), [Amazon Web Services](), [Large Language Model](), [tracing](), [configuration](), [Provisioning]() Tags: [agent](), [agents](), [ai](), [ai-agent](), [ai-agents](), [amazon](), [amazon-bedrock](), [amazon-bedrock-agentcore](), [api](), [aws](), [compliance](), [evaluation](), [infrastructure](), [large-language-model](), [logs](), [model](), [policy](), [production](), [thought-leadership](), [tracing]() ### AI overview This article presents graduated autonomy as an architectural pattern for closing the trust gap in AI agents. Agents gain permissions through sustained reliability and lose them when performance degrades, using trust scoring, autonomy tiers, pre- and post-execution controls, policy enforcement, provenance, reversibility, and delivery gates. The design uses Amazon Bedrock AgentCore, Amazon DynamoDB, and AWS CodePipeline. ### Source excerpt Most teams give AI agents either full access or read-only, leaving value unused or risk unmanaged. This post describes graduated autonomy, an architectural pattern in which agents earn expanded permissions through sustained reliability and lose them when performance degrades, built on Amazon Bedrock AgentCore, Amazon DynamoDB, and AWS CodePipeline. ## How a global payment processor preserved AWS RAM shares and Lake Formation permissions during an AWS Organizations migration DevFeed: [How a global payment processor preserved AWS RAM shares and Lake Formation permissions during an AWS Organizations migration]() Original publisher: [Read original article]() Author: Sam Mukherjee Published: 2026-08-24T15:23:21Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [AWS Lake Formation](), [migration](), [Amazon Web Services](), [Authorization](), [Software as a service]() Tags: [aws](), [aws-lake-formation](), [customer-solutions](), [enterprise](), [migration](), [payment](), [payments](), [resource-access-manager-ram](), [saas](), [us]() ### AI overview AWS describes a migration pattern for preserving AWS RAM shares and AWS Lake Formation permissions while moving 382 accounts between AWS Organizations. Temporary bridge shares maintain continuity during the move, after which the original shares are restored as durable permission objects. ### Source excerpt When AWS accounts move between organizations, organization-bound AWS RAM resource shares break and control-plane access is lost. Learn how a global payment processor used temporary bridge shares to preserve AWS Lake Formation permissions across a 382-account AWS Organizations migration, then restored the original shares as the durable source of truth. ## Build a unified AI agent architecture with DynamoDB and Bedrock DevFeed: [Build a unified AI agent architecture with DynamoDB and Bedrock]() Original publisher: [Read original article]() Author: Dhananjay Karanjkar Published: 2026-08-21T18:19:23Z Content type: tutorial Language: en Sources: [AWS Architecture Blog]() Topics: [AI Bots]() Tags: [advanced-300](), [agent](), [agents](), [ai](), [ai-agent](), [amazon-bedrock](), [amazon-dynamodb](), [amazon-opensearch-service](), [ann](), [api](), [architecture](), [aws-lambda](), [data-architecture](), [database](), [embeddings](), [how-to](), [retrieval](), [search](), [streams](), [sync](), [vector]() ### AI overview A tutorial for building an Amazon Bedrock agent that uses one DynamoDB table for structured data and semantic vector search. DynamoDB Streams generates embeddings when content changes, keeping the vector index synchronized. ### Source excerpt With native vector search in Amazon DynamoDB, you can store vector embeddings alongside your operational data in a single table. This post shows how to build a unified AI agent architecture where an Amazon Bedrock agent uses one DynamoDB table for both structured lookups and semantic search, with a DynamoDB Streams pipeline that keeps embeddings in sync. ## How AgentFlo built AI sales agents with Amazon Bedrock AgentCore - Part 2 DevFeed: [How AgentFlo built AI sales agents with Amazon Bedrock AgentCore - Part 2]() Original publisher: [Read original article]() Author: Muhammad Musab Iqbal Published: 2026-08-21T10:01:18Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [AI Bots](), [ai observability]() Tags: [advanced-300](), [agents](), [ai](), [ai-agents](), [amazon-bedrock](), [amazon-bedrock-agentcore](), [architecture](), [autonomous](), [autonomous-agents](), [aws](), [aws-fargate](), [customer-solutions](), [observability](), [policy](), [sales](), [security](), [serverless]() ### AI overview AgentFlo's second architecture post explains how it uses Amazon Bedrock AgentCore and AWS serverless components to operate AI sales agents with layered safeguards. It emphasizes controls before requests, during tool execution, and after responses, while reporting an early 12% net-revenue uplift. ### Source excerpt Part 2: how AgentFlo built trusted, reliable AI sales agents on Amazon Bedrock AgentCore and AWS serverless architecture. Learn the three-layer guardrails, grounded data foundation, and end-to-end observability behind a +12% net revenue uplift, plus what's next for real-time voice and server-side tool execution. ## How AgentFlo built AI sales agents with Amazon Bedrock AgentCore - Part 1 DevFeed: [How AgentFlo built AI sales agents with Amazon Bedrock AgentCore - Part 1]() Original publisher: [Read original article]() Author: Muhammad Musab Iqbal Published: 2026-08-20T00:32:52Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [AI Bots](), [AI Chat]() Tags: [ai-agents](), [amazon-bedrock-agentcore](), [customer-solutions](), [sales](), [scalability](), [strands-agents](), [whatsapp]() ### AI overview AgentFlo describes building always-on AI sales agents with Amazon Bedrock AgentCore and the Strands Agents SDK. Part 1 focuses on velocity, standardization, and scalability for commerce conversations. ### Source excerpt Learn how AgentFlo built always-on AI sales agents on Amazon Bedrock AgentCore and the Strands Agents SDK. Part 1 covers three pillars of production-grade agents--velocity, standardization, and scalability--including recipe-based deployment, tool routing through AgentCore Gateway, and elastic, stateful commerce conversations. ## How Clario technology detects PHI/PII in DICOM images using Amazon Bedrock DevFeed: [How Clario technology detects PHI/PII in DICOM images using Amazon Bedrock]() Original publisher: [Read original article]() Author: Alex Boudreau Published: 2026-08-19T14:29:31Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [Amazon Bedrock](), [Medical imaging](), [Amazon Textract](), [Amazon Web Services](), [data]() Tags: [amazon](), [amazon-bedrock](), [amazon-textract](), [analysis](), [architecture](), [aws](), [customer-solutions](), [data](), [healthcare](), [images](), [medical-imaging](), [pii](), [technology](), [workflow]() ### AI overview Clario uses Amazon Bedrock and Amazon Textract to automate the detection of PHI and PII in DICOM image slices from clinical trials, including information stored in metadata and text embedded in image pixels. ### Source excerpt Clario, part of Thermo Fisher Scientific, uses Amazon Bedrock and Amazon Textract to automatically detect protected health information (PHI) and personally identifiable information (PII) across thousands of DICOM image slices in clinical trials, covering both metadata tags and text burned into the image pixels. ## AI-powered clinical trial eligibility and safety using Amazon Bedrock AgentCore DevFeed: [AI-powered clinical trial eligibility and safety using Amazon Bedrock AgentCore]() Original publisher: [Read original article]() Author: Sachin Jain Published: 2026-08-19T13:11:51Z Content type: tutorial Language: en Sources: [AWS Architecture Blog]() Topics: [AI Bots]() Tags: [advanced-300](), [agent](), [agents](), [ai](), [ai-agents](), [amazon](), [amazon-bedrock](), [amazon-bedrock-agentcore](), [aws](), [data](), [how-to](), [knowledge-graph](), [llm](), [reasoning](), [safety](), [thought-leadership]() ### AI overview An AWS architecture tutorial for a clinical-trial eligibility and safety agent. It uses Amazon Bedrock AgentCore, AWS HealthLake, knowledge-graph evidence, evaluations, and human-in-the-loop review to support clinician-led screening decisions. ### Source excerpt AI agents built on Amazon Bedrock AgentCore help clinical trial teams make fast, accurate enrollment decisions while keeping clinicians in control. This post shows how to architect an eligibility and safety screening agent using AWS HealthLake, AgentCore, and AgentCore Evaluations. ## Consistency is the new latency: AI at the data layer DevFeed: [Consistency is the new latency: AI at the data layer]() Original publisher: [Read original article]() Author: Suman Chatterjee Published: 2026-08-18T11:13:20Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [AI Bots](), [Language models](), [web applications]() Tags: [advanced-300](), [agents](), [ai](), [amazon-aurora](), [amazon-dynamodb](), [best-practices](), [data](), [latency](), [rag](), [replication]() ### AI overview The article argues that autonomous AI agents need consistent, current data to make reliable decisions. It explains how replication lag can cause stale reads in RAG-based agent systems and points to selecting replication models that match each workload's consistency needs. ### Source excerpt As AI agents move from chatbots to taking action, their reliability depends on the consistency of the data layer beneath them. This post examines how replication lag poisons an agent's context and shows how to match Amazon Aurora, Amazon DynamoDB, and Amazon Keyspaces replication models to each task's consistency requirements. ## Serverless vehicle tracking at scale: Bosch L.OS on AWS DevFeed: [Serverless vehicle tracking at scale: Bosch L.OS on AWS]() Original publisher: [Read original article]() Author: Yogish Kutkunje Pai Published: 2026-08-14T10:02:13Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [Amazon Web Services](), [Serverless](), [real-time](), [Amazon Elastic Container Service](), [AWS Lambda](), [cloud-infrastructure](), [data](), [Networks](), [Amazon EC2]() Tags: [amazon-elastic-container-service](), [architecture](), [aws](), [complexity](), [compliance](), [cost](), [customer-solutions](), [data](), [india](), [integration](), [intermediate-200](), [networks](), [operations](), [performance](), [platform](), [real-time](), [scale](), [serverless](), [supply-chain](), [workflows]() ### AI overview Bosch Mobility Platform Solutions built L.OS, a serverless platform on AWS that unifies fragmented vehicle-tracking data across India's spot logistics market. The article describes how the platform standardizes data from multiple providers and supports scalable, real-time visibility through workflows for discovery, tracking, and termination. ### Source excerpt Learn how Bosch Mobility Platform Solutions built L.OS, a serverless vehicle tracking platform on AWS that unifies India's fragmented spot logistics market into a single real-time visibility layer using Amazon ECS, AWS Lambda, and Amazon MSK. ## Track generative AI costs with Amazon Bedrock inference profiles DevFeed: [Track generative AI costs with Amazon Bedrock inference profiles]() Original publisher: [Read original article]() Author: Erik Mack Published: 2026-08-13T15:59:39Z Content type: tutorial Language: en Sources: [AWS Architecture Blog]() Topics: [Amazon Bedrock](), [Generative AI](), [Inference](), [foundation-models](), [Amazon Web Services](), [AWS IAM]() Tags: [ai](), [amazon-bedrock](), [architecture](), [aws](), [bedrock](), [cost](), [generative](), [generative-ai](), [how-to](), [iam](), [inference](), [intermediate-200](), [technical-how-to]() ### AI overview This tutorial explains how to track generative AI costs by department when multiple teams share a foundation model through Amazon Bedrock. It uses tagged application inference profiles, AWS cost allocation tags, department-based request routing, and AWS Cost Explorer to produce separate cost breakdowns. ### Source excerpt Learn how to track generative AI costs by department using Amazon Bedrock application inference profiles and AWS cost allocation tags. Create tagged profiles for each team and view per-department cost breakdowns in AWS Cost Explorer. ## Recovery strategies to meet data residency requirements DevFeed: [Recovery strategies to meet data residency requirements]() Original publisher: [Read original article]() Author: Jamie Pasterick Published: 2026-08-13T14:05:39Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [data](), [Cryptography]() Tags: [advanced-300](), [aws](), [best-practices](), [cloud](), [data](), [disaster-recovery](), [encryption](), [infrastructure](), [replication]() ### AI overview The article presents three disaster-recovery strategies for critical AWS workloads that must meet data-residency requirements, ranging from encryption-based controls for multi-Region replication to fully in-country architectures. ### Source excerpt Learn three strategies for achieving disaster recovery while meeting data residency requirements. Ranging from encryption-based controls on multi-Region replication to fully in-country architectures, these patterns help you balance recovery objectives with regulatory constraints. ## Reducing Text2SQL latency with parameterized query templates DevFeed: [Reducing Text2SQL latency with parameterized query templates]() Original publisher: [Read original article]() Author: Yury Brukau Published: 2026-08-13T00:40:32Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [text2sql](), [Language models]() Tags: [ai](), [amazon-bedrock](), [architecture](), [aws-lambda](), [database](), [intermediate-200](), [latency](), [llm](), [performance](), [production](), [sql](), [technical-how-to](), [text2sql]() ### AI overview The article describes using parameterized SQL query templates as a semantic caching layer for a production Text2SQL system. It reports lower latency and token consumption by matching similar questions to templates and avoiding some LLM calls. ### Source excerpt Learn how parameterized query templates reduced Text2SQL latency by 80% and cut token consumption by over 50%. This post covers the architecture behind an intelligent caching layer that uses semantic similarity to match user questions to SQL templates, bypassing expensive LLM calls. ## Adobe Firefly: Simplified observability with Amazon Managed Prometheus DevFeed: [Adobe Firefly: Simplified observability with Amazon Managed Prometheus]() Original publisher: [Read original article]() Author: Dev Arora Published: 2026-08-13T00:14:19Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [observability](), [GPU](), [Amazon EKS](), [Amazon Web Services](), [Monitoring](), [telemetry](), [migration](), [Training AI Models]() Tags: [adobe](), [amazon](), [amazon-eks](), [amazon-elastic-kubernetes-service](), [amazon-managed-service-for-prometheus](), [amazon-web-services-aws](), [aws](), [compute](), [cpu](), [customer-solutions](), [data](), [deployment](), [efficiency](), [gpu](), [infrastructure](), [jobs](), [kubernetes](), [metrics](), [observability](), [performance](), [prometheus]() ### AI overview Adobe Firefly migrated critical GPU infrastructure metrics from self-managed Prometheus to Amazon Managed Service for Prometheus. The article describes the observability challenges of large-scale model training on Amazon EKS, including high-cardinality GPU, compute, memory, and network telemetry, and reports 28x faster GPU metric queries with improved reliability and operational efficiency. ### Source excerpt Learn how Adobe Firefly achieved 28x faster GPU metric queries by migrating from self-managed Prometheus to Amazon Managed Service for Prometheus, with improvements in query performance, infrastructure reliability, and operational efficiency.