{"version":"https://jsonfeed.org/version/1.1","title":"AWS — Lab Ledger Desk","home_page_url":"https://labledgerdesk.pages.dev/lab/aws/","feed_url":"https://labledgerdesk.pages.dev/lab/aws/feed.json","description":"Official AWS announcements filed by Lab Ledger Desk.","items":[{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/announcing-ai-data-preparation-capabilities-in-amazon-sagemaker-build/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/announcing-ai-data-preparation-capabilities-in-amazon-sagemaker-build/","title":"Announcing AI data preparation capabilities in Amazon SageMaker: Build high-quality datasets for model development workflows","content_text":"Amazon SageMaker AI now offers AI data preparation capabilities for building high-quality training and evaluation data. Generate synthetic examples, assess and improve datasets, auto-label at scale, and bring in expert review through Python SDK APIs and an agent skill, all from your own notebook or IDE.","date_published":"2026-11-17T19:40:01.000Z","authors":[{"name":"AWS"}],"tags":["launch","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/announcing-ai-data-preparation-capabilities-in-amazon-sagemaker-build-high-quality-datasets-for-model-development-workflows/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/getting-ai-out-of-the-demo-and-into-businesses-globally/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/getting-ai-out-of-the-demo-and-into-businesses-globally/","title":"Getting AI out of the demo and into businesses globally","content_text":"Most enterprises have AI that works in a demo but stalls before production. AWS Forward Deployed Engineering closes that gap. AWS engineers embed with customer teams to take high-value workflows to production in 45-day sprints, leaving a foundation, workflows, and governance the customer owns.","date_published":"2026-11-17T19:05:22.000Z","authors":[{"name":"AWS"}],"tags":["note"],"external_url":"https://aws.amazon.com/blogs/machine-learning/getting-ai-out-of-the-demo-and-into-businesses-globally/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/build-whatsapp-ai-agents-with-amazon-bedrock-agentcore/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/build-whatsapp-ai-agents-with-amazon-bedrock-agentcore/","title":"Build WhatsApp AI agents with Amazon Bedrock AgentCore","content_text":"SMART, an open-source Python SDK and Terraform stack, deploys the full WhatsApp channel layer to your AWS account with one command. Bring any agent that runs on Amazon Bedrock AgentCore, and SMART handles webhook ingestion, media, conversation memory, scheduling, and Meta message templates.","date_published":"2026-11-17T18:48:50.000Z","authors":[{"name":"AWS"}],"tags":["note","open","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/build-whatsapp-ai-agents-with-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/reason-over-time-series-data-with-opentslm-on-amazon-sagemaker-jumpstart/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/reason-over-time-series-data-with-opentslm-on-amazon-sagemaker-jumpstart/","title":"Reason over time-series data with OpenTSLM on Amazon SageMaker JumpStart","content_text":"OpenTSLM, an open source family of time-series language models, is now available in Amazon SageMaker JumpStart. See how Nexthink and Aionic Labs apply it to proactive IT support, then deploy OpenTSLM to a real-time endpoint and fine-tune it on your own data with TimeNet and a SageMaker training job.","date_published":"2026-11-17T18:06:44.000Z","authors":[{"name":"AWS"}],"tags":["launch","llm","open"],"external_url":"https://aws.amazon.com/blogs/machine-learning/reason-over-time-series-data-with-opentslm-on-amazon-sagemaker-jumpstart/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/your-complete-guide-to-aws-quick-at-aws-re-invent-2026/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/your-complete-guide-to-aws-quick-at-aws-re-invent-2026/","title":"Your complete guide to AWS Quick at AWS re:Invent 2026","content_text":"AWS Quick gives your whole organization AI that knows your business, respects your security rules, and acts on your behalf. At AWS re:Invent 2026, customers including Allianz, Cox Automotive, and Southwest Airlines share how they govern, extend, and scale Quick. Use this guide to find the sessions that fit your goals.","date_published":"2026-11-17T17:08:21.000Z","authors":[{"name":"AWS"}],"tags":["note"],"external_url":"https://aws.amazon.com/blogs/machine-learning/your-complete-guide-to-aws-quick-at-aws-reinvent-2026/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/how-loanpro-built-an-agentic-ai-loan-servicing-assistant-with-amazon/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/how-loanpro-built-an-agentic-ai-loan-servicing-assistant-with-amazon/","title":"How LoanPro built an agentic AI loan servicing assistant with Amazon Bedrock AgentCore","content_text":"LoanPro worked with AWS Partner AllCloud and the AWS Generative AI Innovation Center to build a multi-agent AI assistant on Amazon Bedrock and Amazon Bedrock AgentCore. It gives loan servicing agents instant borrower context and next-best-action recommendations, reducing customer call times by up to 15 percent.","date_published":"2026-11-17T17:01:08.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-loanpro-built-an-agentic-ai-loan-servicing-assistant-with-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/responsible-ai-for-agentic-ai-a-phased-roadmap-for-platform-and/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/responsible-ai-for-agentic-ai-a-phased-roadmap-for-platform-and/","title":"Responsible AI for agentic AI: A phased roadmap for platform and application teams","content_text":"Enterprises adopting agentic AI at scale need platforms that embed responsible AI from the start. …","date_published":"2026-11-17T16:56:31.000Z","authors":[{"name":"AWS"}],"tags":["note","safety"],"external_url":"https://aws.amazon.com/blogs/machine-learning/responsible-ai-for-agentic-ai-a-phased-roadmap-for-platform-and-application-teams/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/17/how-arisglobal-scaled-generative-ai-inference-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/17/how-arisglobal-scaled-generative-ai-inference-on-amazon-bedrock/","title":"How ArisGlobal scaled generative AI inference on Amazon Bedrock","content_text":"ArisGlobal runs NavaX, its life-sciences AI engine, on Amazon Bedrock. By caching the shared prompt prefix instead of each per-case document, ArisGlobal cut effective input cost by about 50% and overall monthly inference spend by about 40%, while onboarding more tenants without proportional cost growth.","date_published":"2026-11-17T15:57:09.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-arisglobal-scaled-generative-ai-inference-on-amazon-bedrock/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/build-memory-aware-ai-agents-with-agentic-retrieve-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/build-memory-aware-ai-agents-with-agentic-retrieve-on-amazon-bedrock/","title":"Build memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base","content_text":"Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore memory now store conversations, extract facts, and bring long-term memory into a single AgenticRetrieveStream call. …","date_published":"2026-11-16T22:43:30.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/build-memory-aware-ai-agents-with-agentic-retrieve-on-amazon-bedrock-managed-knowledge-base/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/how-duco-transforms-financial-data-automation-with-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/how-duco-transforms-financial-data-automation-with-amazon-bedrock/","title":"How Duco transforms financial data automation with Amazon Bedrock AgentCore","content_text":"Duco, a data automation platform for tier-one banks, rebuilt its agentic AI stack on Amazon Bedrock and Amazon Bedrock AgentCore. …","date_published":"2026-11-16T22:06:08.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/taxonomy-of-multi-agent-design-patterns-anti-patterns-and-lessons-from/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/taxonomy-of-multi-agent-design-patterns-anti-patterns-and-lessons-from/","title":"Taxonomy of multi-agent design patterns, anti-patterns, and lessons from manufacturing","content_text":"Multi-agent coordination is a distributed systems problem, not a model problem. This post gives a field-tested taxonomy of multi-agent design patterns and anti-patterns, a framework for deciding when multiple agents are warranted, and how to build cost-efficient, reliable systems on AWS.","date_published":"2026-11-16T21:53:46.000Z","authors":[{"name":"AWS"}],"tags":["note","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/taxonomy-of-multi-agent-design-patterns-anti-patterns-and-lessons-from-manufacturing/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/how-moengage-built-agentic-customer-engagement-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/how-moengage-built-agentic-customer-engagement-on-amazon-bedrock/","title":"How MoEngage built agentic customer engagement on Amazon Bedrock AgentCore","content_text":"MoEngage built Merlin AI, a set of AI agents on Amazon Bedrock and Amazon Bedrock AgentCore that let marketing and product teams draft, analyze, and adjust campaigns from a single conversation. …","date_published":"2026-11-16T18:16:07.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-moengage-built-agentic-customer-engagement-on-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/modernizing-mainframe-assembler-to-java-using-amazon-bedrock-and-aws/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/modernizing-mainframe-assembler-to-java-using-amazon-bedrock-and-aws/","title":"Modernizing mainframe Assembler to Java using Amazon Bedrock and AWS Transform","content_text":"Legacy mainframe Assembler applications are costly to maintain and hard to staff. …","date_published":"2026-11-16T17:29:29.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/modernizing-mainframe-assembler-to-java-using-amazon-bedrock-and-aws-transform/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/novo-nordisk-modernizes-manufacturing-process-documents-with-amazon/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/novo-nordisk-modernizes-manufacturing-process-documents-with-amazon/","title":"Novo Nordisk modernizes manufacturing process documents with Amazon Bedrock AgentCore","content_text":"Novo Nordisk's Manufacturing Technology team within the Tablet area team built a process-intelligence assistant on Amazon Bedrock AgentCore, using a GraphRAG architecture that pairs a knowledge graph in Amazon Neptune with hybrid search in Amazon OpenSearch Serverless to turn millions of controlled manufacturing…","date_published":"2026-11-16T17:04:11.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/novo-nordisk-modernizes-manufacturing-process-documents-with-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/get-answers-from-tables-with-tabular-search-in-amazon-bedrock-managed/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/get-answers-from-tables-with-tabular-search-in-amazon-bedrock-managed/","title":"Get answers from tables with tabular search in Amazon Bedrock Managed Knowledge Base","content_text":"Amazon Bedrock Managed Knowledge Base now supports tabular search, so agentic retrieval can answer questions over CSV, XLSX, and XLS files. It looks up values and runs calculations across every relevant row, then combines the results with facts from related documents to answer multi-step analytical questions.","date_published":"2026-11-16T16:12:16.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/get-answers-from-tables-with-tabular-search-in-amazon-bedrock-managed-knowledge-base/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/best-practices-for-writing-denied-topics-in-amazon-bedrock-guardrails/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/best-practices-for-writing-denied-topics-in-amazon-bedrock-guardrails/","title":"Best practices for writing Denied Topics in Amazon Bedrock Guardrails","content_text":"With Denied Topics in Amazon Bedrock Guardrails, you block a content category by describing it in plain language, and the guardrail matches by meaning rather than keyword, which can block more than you intend. …","date_published":"2026-11-16T15:48:01.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/best-practices-for-writing-denied-topics-in-amazon-bedrock-guardrails/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/customize-answers-per-tenant-in-amazon-bedrock-managed-knowledge-base/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/customize-answers-per-tenant-in-amazon-bedrock-managed-knowledge-base/","title":"Customize answers per tenant in Amazon Bedrock Managed Knowledge Base","content_text":"Retrieval instructions in Amazon Bedrock Managed Knowledge Base set the voice, format, retrieval guidance, and answer policy for each tenant on shared knowledge bases. …","date_published":"2026-11-16T15:46:28.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/customize-answers-per-tenant-in-amazon-bedrock-managed-knowledge-base/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/16/use-prompt-caching-with-open-weight-models-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/16/use-prompt-caching-with-open-weight-models-on-amazon-bedrock/","title":"Use prompt caching with open-weight models on Amazon Bedrock","content_text":"Many generative AI applications resend the same long context on every request. Prompt caching lets open-weight models on Amazon Bedrock reuse it to reduce input cost and latency. This post shows implicit and explicit caching through the Chat Completions API and applies caching to an OpenCode coding agent session.","date_published":"2026-11-16T15:42:41.000Z","authors":[{"name":"AWS"}],"tags":["note","open","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/use-prompt-caching-with-open-weight-models-on-amazon-bedrock/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/production-mlops-at-gs-caltex-with-amazon-sagemaker-canvas-part-1/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/production-mlops-at-gs-caltex-with-amazon-sagemaker-canvas-part-1/","title":"Production MLOps at GS Caltex with Amazon SageMaker Canvas, part 1","content_text":"GS Caltex connects Amazon SageMaker Canvas to Amazon SageMaker Pipelines so process engineers' no-code models run in production. This post shows how ML engineers reuse validated preprocessing flows and models, cutting deployment from about a week to a few hours and running batch inference every 30 minutes.","date_published":"2026-11-13T23:22:09.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/production-mlops-at-gs-caltex-with-amazon-sagemaker-canvas-part-1/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/route-coding-agent-requests-to-the-right-model-on-amazon-bedrock-with/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/route-coding-agent-requests-to-the-right-model-on-amazon-bedrock-with/","title":"Route coding agent requests to the right model on Amazon Bedrock with NVIDIA NeMo Switchyard","content_text":"Coding agents work in tasks, and the number that matters is cost per solved task, not price per token. In this post, you use the AWS CDK to deploy LiteLLM with the NVIDIA NeMo Switchyard routing plugin on Amazon Bedrock, then measure cost per solved task for a routed model group against single-model baselines.","date_published":"2026-11-13T22:30:12.000Z","authors":[{"name":"AWS"}],"tags":["note","hardware","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/route-coding-agent-requests-to-the-right-model-on-amazon-bedrock-with-nvidia-nemo-switchyard/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/architecture-patterns-for-fast-session-startup-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/architecture-patterns-for-fast-session-startup-on-amazon-bedrock/","title":"Architecture patterns for fast session startup on Amazon Bedrock AgentCore runtime","content_text":"Amazon Bedrock AgentCore runtime V2 snapshots your initialized environment and restores it for each new session, so session start no longer grows with image size. This post explains how V2 starts a session, how to measure session start time, and four patterns to keep work off the first request.","date_published":"2026-11-13T22:02:39.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/architecture-patterns-for-fast-session-startup-on-amazon-bedrock-agentcore-runtime/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/openfold3-on-amazon-sagemaker-jumpstart-predict-biomolecular-structures/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/openfold3-on-amazon-sagemaker-jumpstart-predict-biomolecular-structures/","title":"OpenFold3 on Amazon SageMaker JumpStart: Predict biomolecular structures","content_text":"Deploy OpenFold3-preview from Amazon SageMaker JumpStart to predict 3D structures of proteins, DNA, RNA, and ligand complexes in your own AWS account. The post covers asynchronous inference, multi-GPU parallelism, bringing your own MSAs for accuracy and privacy, and scaling to zero to reduce cost.","date_published":"2026-11-13T21:53:40.000Z","authors":[{"name":"AWS"}],"tags":["note","hardware","medical"],"external_url":"https://aws.amazon.com/blogs/machine-learning/openfold3-on-amazon-sagemaker-jumpstart-predict-biomolecular-structures/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/cost-optimizing-assemblyai-speech-to-text-inference-on-aws-with-amazon/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/cost-optimizing-assemblyai-speech-to-text-inference-on-aws-with-amazon/","title":"Cost-optimizing AssemblyAI speech-to-text inference on AWS with Amazon EC2 Spot","content_text":"Learn how AssemblyAI runs cost-optimized speech-to-text inference at scale on AWS, using Amazon ECS, Amazon EC2 Spot GPU instances, and an Amazon SQS-based retry architecture to achieve 70% cost savings while maintaining SLA commitments across European Regions.","date_published":"2026-11-13T19:35:35.000Z","authors":[{"name":"AWS"}],"tags":["note","hardware"],"external_url":"https://aws.amazon.com/blogs/machine-learning/cost-optimizing-assemblyai-speech-to-text-inference-on-aws-with-amazon-ec2-spot/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/cost-attribution-and-controls-for-ai-developer-and-productivity-tools/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/cost-attribution-and-controls-for-ai-developer-and-productivity-tools/","title":"Cost attribution and controls for AI developer and productivity tools on Amazon Bedrock","content_text":"Amazon Bedrock provides built-in, zero-instrumentation cost attribution that traces every inference call back to the IAM principal that made it. …","date_published":"2026-11-13T18:44:02.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/cost-attribution-and-controls-for-ai-developer-and-productivity-tools-on-amazon-bedrock/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/13/build-a-model-improvement-flywheel-with-amazon-sagemaker-hyperpod-data/","url":"https://labledgerdesk.pages.dev/b/2026/11/13/build-a-model-improvement-flywheel-with-amazon-sagemaker-hyperpod-data/","title":"Build a model improvement flywheel with Amazon SageMaker HyperPod Data Capture","content_text":"Amazon SageMaker HyperPod Data Capture records live inference inputs and outputs to Amazon S3. …","date_published":"2026-11-13T18:01:15.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/build-a-model-improvement-flywheel-with-amazon-sagemaker-hyperpod-data-capture/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/deploy-frontier-ai-models-on-aws-trainium-with-sglang-neuron/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/deploy-frontier-ai-models-on-aws-trainium-with-sglang-neuron/","title":"Deploy frontier AI models on AWS Trainium with SGLang-Neuron","content_text":"SGLang-Neuron is now publicly available through an AWS Deep Learning Container. With SGLang-Neuron, you can serve models and generate reinforcement learning rollouts with SGLang on AWS Trainium using the same SGLang interface you already know, all running on native PyTorch.","date_published":"2026-11-12T22:03:34.000Z","authors":[{"name":"AWS"}],"tags":["note"],"external_url":"https://aws.amazon.com/blogs/machine-learning/deploy-frontier-ai-models-on-aws-trainium-with-sglang-neuron/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/how-natera-designed-an-agentic-ai-system-for-lab-ops-with-amazon/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/how-natera-designed-an-agentic-ai-system-for-lab-ops-with-amazon/","title":"How Natera designed an agentic AI system for lab ops with Amazon Bedrock AgentCore","content_text":"Natera built SWARM, an agentic AI system on Amazon Bedrock AgentCore that captures institutional lab-operations knowledge and deploys it at scale. …","date_published":"2026-11-12T21:47:07.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-natera-designed-an-agentic-ai-system-for-lab-ops-with-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/four-amazon-bedrock-inference-choices-that-affect-cost/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/four-amazon-bedrock-inference-choices-that-affect-cost/","title":"Four Amazon Bedrock inference choices that affect cost","content_text":"Your Amazon Bedrock inference bill can keep climbing even after you tune prompts and application logic. Four request-level choices (cache duration, service tier, reasoning effort, and maxTokens) change how many tokens the service processes and the rate applied. We show how we tested each and how to verify the effect.","date_published":"2026-11-12T20:51:55.000Z","authors":[{"name":"AWS"}],"tags":["note","llm","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/four-amazon-bedrock-inference-choices-that-affect-cost/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/tokenomics-at-scale-track-and-cap-amazon-bedrock-spend-per-iam/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/tokenomics-at-scale-track-and-cap-amazon-bedrock-spend-per-iam/","title":"Tokenomics at scale: Track and cap Amazon Bedrock spend per IAM principal with CUR 2.0 and AWS Budgets","content_text":"Get per-identity Amazon Bedrock cost visibility and enforceable spend limits using only AWS-native features, with no application code for the common case. …","date_published":"2026-11-12T19:29:55.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/tokenomics-at-scale-track-and-cap-amazon-bedrock-spend-per-iam-principal-with-cur-2-0-and-aws-budgets/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/optimizing-cost-per-task-and-proving-agent-roi-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/optimizing-cost-per-task-and-proving-agent-roi-on-amazon-bedrock/","title":"Optimizing cost per task and proving agent ROI on Amazon Bedrock","content_text":"Comparing per-token prices hides the real cost of running a model on Amazon Bedrock. …","date_published":"2026-11-12T18:43:19.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/optimizing-cost-per-task-and-proving-agent-roi-on-amazon-bedrock/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/building-a-self-service-llm-gateway-with-amazon-bedrock-and-litellm/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/building-a-self-service-llm-gateway-with-amazon-bedrock-and-litellm/","title":"Building a self-service LLM gateway with Amazon Bedrock and LiteLLM","content_text":"Build a self-service LLM gateway with LiteLLM on AWS Fargate that puts Amazon Bedrock foundation models behind an OpenAI-compatible API. Developers get instant access through a single API key, while platform teams gain per-user cost controls, quota isolation, and observability.","date_published":"2026-11-12T18:41:12.000Z","authors":[{"name":"AWS"}],"tags":["note","llm","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/building-a-self-service-llm-gateway-with-amazon-bedrock-and-litellm/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/run-agents-securely-and-efficiently-with-the-next-generation-agentcore/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/run-agents-securely-and-efficiently-with-the-next-generation-agentcore/","title":"Run agents securely and efficiently with the next generation AgentCore runtime","content_text":"AI agents now run multi-step workloads for hours and act on behalf of users, raising the bar for secure, scalable agent compute. …","date_published":"2026-11-12T17:59:59.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/run-agents-securely-and-efficiently-with-the-next-generation-agentcore-runtime/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/migrate-to-amazon-bedrock-managed-knowledge-base-with-your-coding-agent/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/migrate-to-amazon-bedrock-managed-knowledge-base-with-your-coding-agent/","title":"Migrate to Amazon Bedrock Managed Knowledge Base with your coding agent","content_text":"The migration guide in the amazon-bedrock skill helps you migrate a customer-managed Amazon Bedrock knowledge base to a Managed Knowledge Base. …","date_published":"2026-11-12T16:16:45.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","science"],"external_url":"https://aws.amazon.com/blogs/machine-learning/migrate-to-amazon-bedrock-managed-knowledge-base-with-your-coding-agent/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/build-composable-interoperable-multi-agent-systems-with-a2a-on-aws/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/build-composable-interoperable-multi-agent-systems-with-a2a-on-aws/","title":"Build composable, interoperable multi-agent systems with A2A on AWS","content_text":"Build a composable, interoperable multi-agent system on AWS with the Agent-to-Agent (A2A) protocol. …","date_published":"2026-11-12T15:42:21.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/build-composable-interoperable-multi-agent-systems-with-a2a-on-aws/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/fine-grained-access-control-for-amazon-bedrock-managed-knowledge-base/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/fine-grained-access-control-for-amazon-bedrock-managed-knowledge-base/","title":"Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools","content_text":"Learn how to expose an Amazon Bedrock Managed Knowledge Base to AI agents as MCP tools through Amazon Bedrock AgentCore Gateway while keeping per-user access control. …","date_published":"2026-11-12T15:40:24.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/fine-grained-access-control-for-amazon-bedrock-managed-knowledge-base-tools/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/from-prototype-to-production-engineering-agents-with-agent-dlc/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/from-prototype-to-production-engineering-agents-with-agent-dlc/","title":"From prototype to production: Engineering agents with Agent DLC","content_text":"Agents stall between demo and release when teams lack a repeatable way to measure how good an agent is and whether the last change helped. …","date_published":"2026-11-12T15:38:47.000Z","authors":[{"name":"AWS"}],"tags":["launch","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/from-prototype-to-production-engineering-agents-with-agent-dlc/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/12/build-autonomous-ai-agents-with-amazon-bedrock-and-spring-ai/","url":"https://labledgerdesk.pages.dev/b/2026/11/12/build-autonomous-ai-agents-with-amazon-bedrock-and-spring-ai/","title":"Build autonomous AI agents with Amazon Bedrock and Spring AI","content_text":"Learn how Java developers can build production-ready autonomous AI agents using Amazon Bedrock and Spring AI. This post walks through tool calling, conversation memory, resilience patterns, and multi-agent orchestration, then deploys the agent to AWS with Amazon Bedrock AgentCore.","date_published":"2026-11-12T01:18:23.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/build-autonomous-ai-agents-with-amazon-bedrock-and-spring-ai/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/openai-codex-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/openai-codex-on-amazon-bedrock/","title":"OpenAI Codex on Amazon Bedrock","content_text":"A practical guide for enterprises rolling out OpenAI Codex to developers on AWS, with Amazon Bedrock as the model backend, covering the access, governance, and cost decisions that platform, security, and finance teams need to align on.","date_published":"2026-11-11T23:35:47.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/openai-codex-on-amazon-bedrock/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/semantic-diffing-of-formal-policies-with-anti-unification/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/semantic-diffing-of-formal-policies-with-anti-unification/","title":"Semantic diffing of formal policies with anti-unification","content_text":"A textual diff of two formal policies flags every cosmetic change and hides the one that alters behavior. This post shows how to compute a symbolic, deterministic semantic diff with an open-source anti-unification engine, so reviewers see only the genuine disagreements between two candidate authorization policies.","date_published":"2026-11-11T23:33:03.000Z","authors":[{"name":"AWS"}],"tags":["note","open"],"external_url":"https://aws.amazon.com/blogs/machine-learning/semantic-diffing-of-formal-policies-with-anti-unification/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/detecting-and-recovering-from-silent-data-corruption-on-amazon/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/detecting-and-recovering-from-silent-data-corruption-on-amazon/","title":"Detecting and recovering from silent data corruption on Amazon SageMaker HyperPod","content_text":"Silent data corruption is a GPU fault that returns wrong but plausible numbers with no error, quietly poisoning distributed training. This post adds three checks to a PyTorch DDP loop to detect it, localize the faulty node on Amazon SageMaker HyperPod, and hand the node to automatic recovery for replacement.","date_published":"2026-11-11T23:30:03.000Z","authors":[{"name":"AWS"}],"tags":["note","hardware","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/detecting-and-recovering-from-silent-data-corruption-on-amazon-sagemaker-hyperpod/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/introducing-the-web-search-api-on-amazon-bedrock-agentcore/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/introducing-the-web-search-api-on-amazon-bedrock-agentcore/","title":"Introducing the Web Search API on Amazon Bedrock AgentCore","content_text":"Today we're announcing the Web Search API on Amazon Bedrock AgentCore: your own code can search the web with a single signed API call, with no gateway and no resources to create. Call it from the AWS SDKs or the AWS CLI and use it in applications, agent loops, and data pipelines.","date_published":"2026-11-11T23:13:16.000Z","authors":[{"name":"AWS"}],"tags":["launch","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/introducing-the-web-search-api-on-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/icymi-what-landed-for-ai-builders-in-october-2026/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/icymi-what-landed-for-ai-builders-in-october-2026/","title":"ICYMI: What landed for AI builders in October 2026","content_text":"A recap of the major Amazon Bedrock, Amazon Bedrock AgentCore, and Strands updates from October 2026: new models to match each task, updates that keep agents available and grounded, and clearer cost reporting for AI builders.","date_published":"2026-11-11T22:26:40.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/icymi-what-landed-for-ai-builders-in-october-2026/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/the-attendee-s-guide-to-the-aws-re-invent-2026-ai-ml-track/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/the-attendee-s-guide-to-the-aws-re-invent-2026-ai-ml-track/","title":"The attendee’s guide to the AWS re:Invent 2026 AI/ML track","content_text":"AWS re:Invent 2026 includes more than 140 AI/ML track sessions. …","date_published":"2026-11-11T21:05:59.000Z","authors":[{"name":"AWS"}],"tags":["note","hardware","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/the-attendees-guide-to-the-aws-reinvent-2026-ai-ml-track/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/automating-aws-agent-registry-updates-with-push-based-architecture/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/automating-aws-agent-registry-updates-with-push-based-architecture/","title":"Automating AWS Agent Registry updates with push-based architecture","content_text":"This post shows how to keep the AWS Agent Registry current automatically. …","date_published":"2026-11-11T20:52:48.000Z","authors":[{"name":"AWS"}],"tags":["note","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/automating-aws-agent-registry-updates-with-push-based-architecture/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/how-dxc-technology-built-a-multi-model-ai-substrate-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/how-dxc-technology-built-a-multi-model-ai-substrate-on-amazon-bedrock/","title":"How DXC Technology built a multi-model AI substrate on Amazon Bedrock","content_text":"DXC Technology runs mission-critical managed IT services for regulated organizations across 70 countries. …","date_published":"2026-11-11T20:45:45.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-dxc-technology-built-a-multi-model-ai-substrate-on-amazon-bedrock/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/accelerating-generative-ai-delivery-with-reusable-assets/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/accelerating-generative-ai-delivery-with-reusable-assets/","title":"Accelerating generative AI delivery with reusable assets","content_text":"Every generative AI team keeps rebuilding the same components: RAG pipelines, document processors, and agent scaffolding. …","date_published":"2026-11-11T19:19:21.000Z","authors":[{"name":"AWS"}],"tags":["note","open","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/accelerating-generative-ai-delivery-with-reusable-assets/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/accelerating-product-development-with-ai-driven-lifecycle-management-ai/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/accelerating-product-development-with-ai-driven-lifecycle-management-ai/","title":"Accelerating product development with AI-driven lifecycle management (AI-PDLC) in AWS Quick","content_text":"Learn how to build an AI-driven product development lifecycle (AI-PDLC) with a suite of six AWS Quick agents that take you from scattered customer signals to a validated prototype across Discover, Decide, Design, and Prototype, with human approval at every gate and a specification ready to hand to coding agents like…","date_published":"2026-11-11T16:05:33.000Z","authors":[{"name":"AWS"}],"tags":["note","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/accelerating-product-development-with-ai-driven-lifecycle-management-ai-pdlc-in-aws-quick/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/uaef-a-framework-agnostic-system-for-closed-loop-evaluation-of-ai-agents/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/uaef-a-framework-agnostic-system-for-closed-loop-evaluation-of-ai-agents/","title":"UAEF: A framework-agnostic system for closed-loop evaluation of AI agents","content_text":"The Universal Agent Evaluation Framework (UAEF) is a framework-agnostic system for evaluating AI agents. UAEF converts each framework's traces into one canonical format, scores them with 36 built-in metrics across 7 dimensions, and stores results so teams can compare agent versions and catch regressions.","date_published":"2026-11-11T15:50:55.000Z","authors":[{"name":"AWS"}],"tags":["note","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/uaef-a-framework-agnostic-system-for-closed-loop-evaluation-of-ai-agents/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/introducing-usage-based-pricing-for-amazon-sagemaker-ai-bidirectional/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/introducing-usage-based-pricing-for-amazon-sagemaker-ai-bidirectional/","title":"Introducing usage-based pricing for Amazon SageMaker AI bidirectional streaming","content_text":"AWS Marketplace now supports usage-based metering for Amazon SageMaker bidirectional streaming inference, so model providers can charge for what customers actually consume during a live stream. Deepgram is the launch partner, bringing usage-based speech-to-text and text-to-speech billing to AWS Marketplace.","date_published":"2026-11-11T15:10:23.000Z","authors":[{"name":"AWS"}],"tags":["launch","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/introducing-usage-based-pricing-for-amazon-sagemaker-ai-bidirectional-streaming/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/11/introducing-kimi-k3-1-pro-on-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/11/introducing-kimi-k3-1-pro-on-amazon-bedrock/","title":"Introducing Kimi K3.1 Pro on Amazon Bedrock","content_text":"Kimi K3.1 Pro from Moonshot AI is now available on Amazon Bedrock. Learn how to get started through the OpenAI-compatible Chat Completions, Responses, and Converse APIs, optimize inference with explicit prompt caching, and use the model as a coding assistant in OpenCode.","date_published":"2026-11-11T01:07:19.000Z","authors":[{"name":"AWS"}],"tags":["launch","llm","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/introducing-kimi-k3-1-pro-on-amazon-bedrock/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/10/build-a-daily-dependency-watcher-with-langgraph-and-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/10/build-a-daily-dependency-watcher-with-langgraph-and-amazon-bedrock/","title":"Build a daily dependency watcher with LangGraph and Amazon Bedrock AgentCore web search","content_text":"The Web Search API in Amazon Bedrock AgentCore gives agents current, cited web results signed with the AWS credentials they already use. …","date_published":"2026-11-10T23:34:05.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/build-a-daily-dependency-watcher-with-langgraph-and-amazon-bedrock-agentcore-web-search/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/10/the-agent-evaluation-playbook-built-in-deepeval-and-autoeval-on-amazon/","url":"https://labledgerdesk.pages.dev/b/2026/11/10/the-agent-evaluation-playbook-built-in-deepeval-and-autoeval-on-amazon/","title":"The agent evaluation playbook: Built-in, DeepEval, and AutoEval on Amazon Bedrock AgentCore Evaluations","content_text":"When you deploy an agent, whether it is working is really several questions: did it finish the task, stay on topic, leak data, or skip steps? …","date_published":"2026-11-10T22:35:03.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/the-agent-evaluation-playbook-built-in-deepeval-and-autoeval-on-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/10/autonomous-treasury-agents-how-trovata-built-an-ai-native-solution-on/","url":"https://labledgerdesk.pages.dev/b/2026/11/10/autonomous-treasury-agents-how-trovata-built-an-ai-native-solution-on/","title":"Autonomous treasury agents: How Trovata built an AI-native solution on Amazon Bedrock and AgentCore","content_text":"Learn how Trovata built autonomous treasury agents on Amazon Bedrock and Amazon Bedrock AgentCore, using an RBAC-secured architecture for bank-branded AI deployment and agentic workflows that move corporate treasury from manual operations to real-time decision-making at enterprise scale.","date_published":"2026-11-10T18:11:08.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/autonomous-treasury-agents-how-trovata-built-an-ai-native-solution-on-amazon-bedrock-and-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/10/how-tcs-built-an-agentic-test-orchestrator-with-amazon-bedrock-agentcore/","url":"https://labledgerdesk.pages.dev/b/2026/11/10/how-tcs-built-an-agentic-test-orchestrator-with-amazon-bedrock-agentcore/","title":"How TCS built an agentic test orchestrator with Amazon Bedrock AgentCore","content_text":"Tata Consultancy Services (TCS) built an agentic test orchestrator on Amazon Bedrock AgentCore that turns requirements into executable, governed tests for its Banking, Financial Services, and Insurance (BFSI) clients. …","date_published":"2026-11-10T16:59:43.000Z","authors":[{"name":"AWS"}],"tags":["research","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-tcs-built-an-agentic-test-orchestrator-with-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/10/amazon-bedrock-tokenomics-data-lake/","url":"https://labledgerdesk.pages.dev/b/2026/11/10/amazon-bedrock-tokenomics-data-lake/","title":"Amazon Bedrock tokenomics data lake","content_text":"Running Amazon Bedrock across many accounts shows you the bill but not what happened inside each call. …","date_published":"2026-11-10T16:56:36.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/amazon-bedrock-tokenomics-data-lake/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/10/how-skills-and-agents-work-in-aws-quick/","url":"https://labledgerdesk.pages.dev/b/2026/11/10/how-skills-and-agents-work-in-aws-quick/","title":"How skills and agents work in AWS Quick","content_text":"Repeatable tasks like status updates, release notes, and ticket creation can be encoded in AWS Quick through agents and skills. This post covers how agents, skills, and your data fit together in AWS Quick, how to build and share skills for your team, and how the official catalog and custom agents help you use them.","date_published":"2026-11-10T00:21:34.000Z","authors":[{"name":"AWS"}],"tags":["launch","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-skills-and-agents-work-in-aws-quick/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/09/single-shot-and-agentic-retrieval-with-amazon-bedrock-managed-knowledge/","url":"https://labledgerdesk.pages.dev/b/2026/11/09/single-shot-and-agentic-retrieval-with-amazon-bedrock-managed-knowledge/","title":"Single-shot and agentic retrieval with Amazon Bedrock Managed Knowledge Base","content_text":"Amazon Bedrock Managed Knowledge Base now supports single-shot RAG and retrieval-only requests through AgenticRetrieveStream, alongside agentic retrieval. This post explains how the maxAgentIteration parameter matches retrieval effort to each request, using an illustrative internal banking policy assistant.","date_published":"2026-11-09T20:13:18.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/single-shot-and-agentic-retrieval-with-amazon-bedrock-managed-knowledge-base/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/09/introducing-claude-fable-5-2-on-aws/","url":"https://labledgerdesk.pages.dev/b/2026/11/09/introducing-claude-fable-5-2-on-aws/","title":"Introducing Claude Fable 5.2 on AWS","content_text":"Claude Fable 5.2 and Claude Mythos 5.2 are now available on Amazon Bedrock and Claude Platform on AWS. Learn what's new in both models, why Fable 5.2 matters for your technical workloads, and how to get started building with it on Amazon Bedrock.","date_published":"2026-11-09T20:04:37.000Z","authors":[{"name":"AWS"}],"tags":["launch","llm","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/introducing-claude-fable-5-2-on-aws/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/09/nvidia-nemotron-3-5-super-vl-is-now-available-in-amazon-sagemaker/","url":"https://labledgerdesk.pages.dev/b/2026/11/09/nvidia-nemotron-3-5-super-vl-is-now-available-in-amazon-sagemaker/","title":"NVIDIA Nemotron 3.5 Super VL is now available in Amazon SageMaker JumpStart","content_text":"NVIDIA Nemotron 3.5 Super VL, a 120B-parameter multimodal vision-language model, is now available in Amazon SageMaker JumpStart. Deploy the NVFP4 or BF16 variant in a few steps, then run text, image, and video inference for document intelligence, computer-use agents, and multimodal agentic workloads.","date_published":"2026-11-09T20:01:20.000Z","authors":[{"name":"AWS"}],"tags":["launch","llm","hardware"],"external_url":"https://aws.amazon.com/blogs/machine-learning/nvidia-nemotron-3-5-super-vl-is-now-available-in-amazon-sagemaker-jumpstart/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/09/pluggable-agentic-ai-framework-a-seven-layer-composable-enterprise/","url":"https://labledgerdesk.pages.dev/b/2026/11/09/pluggable-agentic-ai-framework-a-seven-layer-composable-enterprise/","title":"Pluggable Agentic AI Framework: A seven-layer composable enterprise agentic AI reference architecture on Amazon Bedrock AgentCore","content_text":"A seven-layer composable reference architecture for taking enterprise agentic AI from prototype to production on Amazon Bedrock AgentCore. Each layer has a stable contract, so you can swap technologies at any layer without redesigning the rest of the stack.","date_published":"2026-11-09T19:05:54.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/pluggable-agentic-ai-framework-a-seven-layer-composable-enterprise-agentic-ai-reference-architecture-on-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/09/how-crossnokaye-grounds-physical-ai-with-amazon-bedrock-agentcore/","url":"https://labledgerdesk.pages.dev/b/2026/11/09/how-crossnokaye-grounds-physical-ai-with-amazon-bedrock-agentcore/","title":"How CrossnoKaye grounds physical AI with Amazon Bedrock AgentCore","content_text":"CrossnoKaye brought physical AI to heavy industry with Amazon Bedrock AgentCore. Its ATLAS platform and AURA agentic system ground AI reasoning in live plant data and run verifiable Python in isolated AgentCore sandboxes, giving plant engineers checkable, math-backed answers instead of model guesses.","date_published":"2026-11-09T18:55:43.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-crossnokaye-grounds-physical-ai-with-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/09/professional-work-deserves-professional-tools-meet-aws-quick/","url":"https://labledgerdesk.pages.dev/b/2026/11/09/professional-work-deserves-professional-tools-meet-aws-quick/","title":"Professional work deserves professional tools. Meet AWS Quick.","content_text":"Introducing AWS Quick, formerly Amazon Quick, and the debut of our first brand campaign celebrating teams who keep business moving. AWS Quick is the AI workspace built only for work, where teams use AI agents to research, analyze, and act across the data and applications they already rely on.","date_published":"2026-11-09T18:43:30.000Z","authors":[{"name":"AWS"}],"tags":["launch","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/professional-work-deserves-professional-tools-meet-aws-quick/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/sagemaker-inference-now-supports-multi-instance-gpu-to-maximize-gpu/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/sagemaker-inference-now-supports-multi-instance-gpu-to-maximize-gpu/","title":"SageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints","content_text":"Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU (MIG), which divides one GPU into hardware-isolated partitions so you can run a different model in each or take a right-sized fraction of a newer accelerator. …","date_published":"2026-11-06T18:01:00.000Z","authors":[{"name":"AWS"}],"tags":["note","hardware","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/sagemaker-inference-now-supports-multi-instance-gpu-to-maximize-gpu-utilization-for-model-endpoints/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/taxonomy-of-agentic-primitives-in-amazon-quick/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/taxonomy-of-agentic-primitives-in-amazon-quick/","title":"Taxonomy of agentic primitives in Amazon Quick","content_text":"As we built Amazon Quick, its agents grew from answering questions to taking actions, and the same primitives kept getting rebuilt under different names. …","date_published":"2026-11-06T17:34:45.000Z","authors":[{"name":"AWS"}],"tags":["note","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/taxonomy-of-agentic-primitives-in-amazon-quick/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/serverless-mcp-server-for-ai-agent-data-lake-access-on-amazon-ecs/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/serverless-mcp-server-for-ai-agent-data-lake-access-on-amazon-ecs/","title":"Serverless MCP server for AI agent data lake access on Amazon ECS Fargate","content_text":"Learn how to build a serverless Model Context Protocol (MCP) server on Amazon ECS with AWS Fargate that gives AI agents secure, metadata-driven access to an enterprise data lake. Exposing a new dataset requires only a JSON file, with no per-dataset integration code.","date_published":"2026-11-06T17:13:13.000Z","authors":[{"name":"AWS"}],"tags":["research","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/serverless-mcp-server-for-ai-agent-data-lake-access-on-amazon-ecs-fargate/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock/","title":"Govern AI agent access with Okta Cross App Access and Amazon Bedrock AgentCore – Part 2","content_text":"In Part 1 you built one governed agent. …","date_published":"2026-11-06T17:09:23.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock-agentcore-part-2/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock-9080/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock-9080/","title":"Govern AI agent access with Okta Cross App Access and Amazon Bedrock AgentCore – Part 1","content_text":"An AI agent that acts for a user raises an identity question that per-app OAuth and service accounts leave open: which agent may act for which user, and how you stop it. …","date_published":"2026-11-06T17:09:18.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock-agentcore-part-1/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/how-greenlight-financial-built-an-autonomous-soc-solution-on-amazon/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/how-greenlight-financial-built-an-autonomous-soc-solution-on-amazon/","title":"How Greenlight Financial built an autonomous SOC solution on Amazon Bedrock AgentCore","content_text":"Greenlight Financial resolves more than 90% of up to 4,000 monthly security and risk cases without human intervention using Luna, a tiered multi-agent system on Amazon Bedrock AgentCore. …","date_published":"2026-11-06T16:55:05.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-greenlight-financial-built-an-autonomous-soc-solution-on-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/taxbit-assist-a-grounded-role-aware-ai-agent-on-amazon-bedrock-agentcore/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/taxbit-assist-a-grounded-role-aware-ai-agent-on-amazon-bedrock-agentcore/","title":"Taxbit Assist: A grounded, role-aware AI agent on Amazon Bedrock AgentCore","content_text":"Taxbit built Taxbit Assist, a cited, permission-aware AI assistant embedded in its enterprise dashboard, on Amazon Bedrock AgentCore. …","date_published":"2026-11-06T16:49:42.000Z","authors":[{"name":"AWS"}],"tags":["note","safety","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/taxbit-assist-a-grounded-role-aware-ai-agent-on-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/06/extend-claude-code-to-remote-sessions-on-amazon-bedrock-agentcore-with/","url":"https://labledgerdesk.pages.dev/b/2026/11/06/extend-claude-code-to-remote-sessions-on-amazon-bedrock-agentcore-with/","title":"Extend Claude Code to remote sessions on Amazon Bedrock AgentCore with security controls","content_text":"Run Claude Code as a remote agent on Amazon Bedrock AgentCore. Each coding task runs in its own isolated session in your AWS account, every model call goes through Amazon Bedrock, and the result comes back as a GitHub pull request you review and merge.","date_published":"2026-11-06T16:45:58.000Z","authors":[{"name":"AWS"}],"tags":["note","llm","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/extend-claude-code-to-remote-sessions-on-amazon-bedrock-agentcore-with-security-controls/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/05/getting-started-with-web-answer-on-amazon-bedrock-agentcore/","url":"https://labledgerdesk.pages.dev/b/2026/11/05/getting-started-with-web-answer-on-amazon-bedrock-agentcore/","title":"Getting started with Web Answer on Amazon Bedrock AgentCore","content_text":"Web Answer on Amazon Bedrock AgentCore returns a synthesized, source-cited answer to a natural-language question in a single tool call, with no search, retrieve, synthesize, and citation pipeline to build. Learn how it works and how to add it to an AgentCore Gateway and call it from an agent.","date_published":"2026-11-05T21:04:24.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/getting-started-with-web-answer-on-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/05/how-amazon-marketplace-evaluates-content-quality-with-amazon-sagemaker/","url":"https://labledgerdesk.pages.dev/b/2026/11/05/how-amazon-marketplace-evaluates-content-quality-with-amazon-sagemaker/","title":"How Amazon Marketplace evaluates content quality with Amazon SageMaker AI","content_text":"Learn how Amazon Marketplace evaluates A+ Content quality at scale on Amazon SageMaker AI by rendering each product page as a single snapshot, scoring it with a vision-language model fused with OCR readability signals in a CatBoost classifier, and using SHAP to turn each decision into prioritized, actionable…","date_published":"2026-11-05T18:06:43.000Z","authors":[{"name":"AWS"}],"tags":["note","llm","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-amazon-marketplace-evaluates-content-quality-with-amazon-sagemaker-ai/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/use-decision-models-with-amazon-bedrock-agentcore-evaluations/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/use-decision-models-with-amazon-bedrock-agentcore-evaluations/","title":"Use decision models with Amazon Bedrock AgentCore Evaluations","content_text":"Some agent-evaluation questions are narrow and repeatable, and decision models answer exactly that kind of question. …","date_published":"2026-11-04T18:46:36.000Z","authors":[{"name":"AWS"}],"tags":["launch","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/use-decision-models-with-amazon-bedrock-agentcore-evaluations/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/smart-approvals-in-amazon-quick-human-oversight-where-it-matters/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/smart-approvals-in-amazon-quick-human-oversight-where-it-matters/","title":"Smart Approvals in Amazon Quick: Human oversight where it matters","content_text":"Smart Approvals in Amazon Quick reviews eligible agent actions within your existing controls, reducing unnecessary approval prompts while keeping consequential decisions with a person. See how policy sets the boundary, how a classifier reviews actions, and how AWS CloudTrail and Amazon CloudWatch Logs support audit.","date_published":"2026-11-04T16:33:03.000Z","authors":[{"name":"AWS"}],"tags":["note","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/smart-approvals-in-amazon-quick-human-oversight-where-it-matters/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/four-layers-of-context-engineering-for-production-ai-agents-how-deep/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/four-layers-of-context-engineering-for-production-ai-agents-how-deep/","title":"Four layers of context engineering for production AI agents: How Deep Insight applies them in working code","content_text":"In production AI agents, context management is the real bottleneck. …","date_published":"2026-11-04T16:30:40.000Z","authors":[{"name":"AWS"}],"tags":["note","open","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/four-layers-of-context-engineering-for-production-ai-agents-how-deep-insight-applies-them-in-working-code/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/how-indegene-is-modernizing-and-scaling-enterprise-data-quality-in-life/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/how-indegene-is-modernizing-and-scaling-enterprise-data-quality-in-life/","title":"How Indegene is modernizing and scaling enterprise data quality in life sciences","content_text":"This post explores how Indegene built a production-grade, LLM-powered Data Quality Agent in its NEXT Unified Data Platform on AWS. …","date_published":"2026-11-04T16:25:57.000Z","authors":[{"name":"AWS"}],"tags":["note","llm","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-indegene-is-modernizing-and-scaling-enterprise-data-quality-in-life-sciences/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/04/how-u-mobile-built-agentic-telco-operations-with-amazon-bedrock/","url":"https://labledgerdesk.pages.dev/b/2026/11/04/how-u-mobile-built-agentic-telco-operations-with-amazon-bedrock/","title":"How U Mobile built agentic telco operations with Amazon Bedrock AgentCore","content_text":"U Mobile, Malaysia's newest 5G network provider, built AiDaH, an agentic AI operations platform on Amazon Bedrock AgentCore that moves beyond AI assistance to autonomous action across telco operations. …","date_published":"2026-11-04T16:23:33.000Z","authors":[{"name":"AWS"}],"tags":["launch","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-u-mobile-built-agentic-telco-operations-with-amazon-bedrock-agentcore/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/03/bring-structured-and-unstructured-data-together-with-amazon-quick/","url":"https://labledgerdesk.pages.dev/b/2026/11/03/bring-structured-and-unstructured-data-together-with-amazon-quick/","title":"Bring structured and unstructured data together with Amazon Quick","content_text":"Amazon Quick brings structured and unstructured data together in one experience. In this post, you connect Amazon S3 as a knowledge base, enrich a dataset, build a Space, and create a custom chat agent that answers business questions across both data types through a single conversational interface.","date_published":"2026-11-03T16:49:29.000Z","authors":[{"name":"AWS"}],"tags":["research","agents"],"external_url":"https://aws.amazon.com/blogs/machine-learning/bring-structured-and-unstructured-data-together-with-amazon-quick/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/03/servicenow-on-behalf-of-token-exchange-with-bedrock-agentcore-gateway/","url":"https://labledgerdesk.pages.dev/b/2026/11/03/servicenow-on-behalf-of-token-exchange-with-bedrock-agentcore-gateway/","title":"ServiceNow on-behalf-of token exchange with Bedrock AgentCore Gateway","content_text":"Learn how to configure Amazon Bedrock AgentCore Gateway for an on-behalf-of (OBO) token exchange with Microsoft Entra ID, so an AI agent can call the ServiceNow REST API while preserving the calling user's identity. AgentCore Gateway performs the exchange natively, with no interceptor Lambda or custom code.","date_published":"2026-11-03T16:47:40.000Z","authors":[{"name":"AWS"}],"tags":["note","agents","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/servicenow-on-behalf-of-token-exchange-with-bedrock-agentcore-gateway/"},{"id":"https://labledgerdesk.pages.dev/b/2026/11/03/how-gen-digital-built-norton-revamp-s-ai-curated-news-engine-with/","url":"https://labledgerdesk.pages.dev/b/2026/11/03/how-gen-digital-built-norton-revamp-s-ai-curated-news-engine-with/","title":"How Gen Digital built Norton Revamp’s AI-curated News Engine with Amazon Bedrock AgentCore Web Search","content_text":"Gen Digital built Norton Revamp, a generative AI-powered professional reputation management platform, with an AI-curated News Engine grounded by Web Search on Amazon Bedrock AgentCore. …","date_published":"2026-11-03T16:43:20.000Z","authors":[{"name":"AWS"}],"tags":["note","enterprise"],"external_url":"https://aws.amazon.com/blogs/machine-learning/how-gen-digital-built-norton-revamps-ai-curated-news-engine-with-amazon-bedrock-agentcore-web-search/"}]}