TechniqueRLHF / Alignment8 recent entries27 Apr 2026How Popsa used Amazon Nova to inspire customers with personalised title suggestionsIn this post, we share how we applied Amazon Bedrock and the Amazon Nova family of models to reimagine our Title Suggestion feature. By combining metadata, computer vision, and retrieval-augmented gen→29 Apr 2026Run custom MCP proxies serverless on Amazon Bedrock AgentCore RuntimeThis post shows you how to deploy a serverless MCP proxy on Amazon Bedrock AgentCore Runtime that gives you a programmable layer to implement proper governance, controls, and observability aligned wit
TechniqueRAG8 recent entries14 Sept 2026The generative AI customization spectrum: From prompt engineering to custom models on AWSPick the right generative AI customization approach on AWS with an 8-step decision framework, from prompt engineering and RAG to fine-tuning, continued pre-training, and Amazon Nova Forge. Start simpl→15 Sept 2026Optimizing cost and latency with Amazon Bedrock prompt cachingPrompt caching in Amazon Bedrock can cut input token costs by up to 90% when you repeatedly send the same context to foundation models. This post walks through six practical prompt caching scenarios u→17 Sept 2026Selecting a vector store for Amazon Bedrock Knowledge BasesChoosing the right vector store for your Amazon Bedrock Knowledge Bases RAG application affects performance and cost. This post compares Amazon OpenSearch Service, Amazon Aurora PostgreSQL with pgvect→22 Sept 2026Bring more intelligence to everyday work with GPT-6 Sol and GPT-6 Luna on Amazon BedrockAmazon Bedrock has released OpenAI’s GPT‑6 Sol and GPT‑6 Luna as generally available services, offering distinct capabilities for advanced reasoning/coding (Sol) and high‑volume repeatable tasks (Luna→29 Sept 2026Building an AI-powered contract intelligence platform with Amazon Quick and Amazon Bedrock AgentCoreManually extracting data from hundreds of vendor contracts doesn't scale, and RAG chat tools fall short on portfolio-wide questions. This post shares a contract intelligence platform on AWS that uses →30 Sept 2026Query claims in natural language with Amazon Bedrock Knowledge BasesThis technical how-to builds a conversational claims assistant on Amazon Bedrock Knowledge Bases that answers natural-language questions with citations. It covers ingesting claim documents from Amazon→5 Oct 2026Agentic retrieval with LangChain and Amazon Bedrock Knowledge BasesBuild a Retrieval Augmented Generation (RAG) application on Amazon Bedrock Managed Knowledge Base with LangChain, and see how agentic retrieval handles the multi-part questions that single-shot retrie→7 Oct 2026Rethinking access control for RAG with Amazon Quick and Amazon BedrockEnterprise RAG unlocks insights from knowledge sources like SharePoint, Google Drive, and Confluence, but those sources carry complex permissions. Learn how Amazon Quick and Amazon Bedrock Knowledge B
TechniqueAgents8 recent entries7 Oct 2026How Qlik built grounded, enterprise-scale AI with Amazon BedrockQlik built Qlik Answers on Amazon Bedrock to give its 40,000+ customers grounded, sourced answers across structured and unstructured enterprise data. Learn how a layered, multi-agent architecture with→7 Oct 2026How Cornerstone OnDemand cut database diagnosis by 78% with Amazon BedrockCornerstone OnDemand built Orion AI, a multi-agent system on Amazon Bedrock and Strands Agents, to turn database operations from reactive firefighting into proactive automation. A three-person team cu→7 Oct 2026Building AI builders: Playbook for closing the AI knowledge-capability gapThe biggest barrier to AI adoption isn't awareness. It's the gap between talking about AI and building with it. Here's the playbook we used to turn non-technical, customer-facing professionals into co→7 Oct 2026Beyond hours saved: Building the business case for agentic automationThe RPA-era ROI model misses most of the value agentic automation creates. This post gives AI center of excellence leaders a framework to size the full value of agents across time savings, exception h→7 Oct 2026Automate remediation post AWS DevOps Agent investigationAWS DevOps Agent can diagnose production incidents but is kept in observe-and-report mode so it does not change resources directly. This post shows how to use AWS Lambda Durable Functions, Amazon Even→8 Oct 2026Pay-per-inference for AI agents: How BlockRun and Incarna use Amazon Bedrock AgentCore paymentsAmazon Bedrock AgentCore payments gives AI agents a managed way to pay for services on demand, with spending limits enforced by the infrastructure. See how Incarna's agents pay BlockRun for model infe→9 Oct 2026ICYMI: What landed for AI builders in September 2026A monthly recap of the latest Amazon Bedrock, Amazon Bedrock AgentCore, and Strands updates from September 2026: broader model choice, faster serverless agents with built-in evaluation, and automated →9 Oct 2026How Postman runs Agent Mode for 40 million developers on Amazon BedrockBuilding an AI agent that works in a demo is a different problem from running one for 40 million developers. Postman and AWS share the architectural patterns behind Agent Mode: controlling tool sprawl
TechniqueFine-tuning8 recent entries4 Sept 2026Customizing your knowledge base on Amazon Bedrock for large and complex documents using Amazon TextractLearn how to customize an Amazon Bedrock knowledge base for large, complex documents by combining the high-accuracy text extraction of Amazon Textract with the generative AI of Amazon Bedrock. This po→14 Sept 2026The generative AI customization spectrum: From prompt engineering to custom models on AWSPick the right generative AI customization approach on AWS with an 8-step decision framework, from prompt engineering and RAG to fine-tuning, continued pre-training, and Amazon Nova Forge. Start simpl→15 Sept 2026Build an AI-powered product tagging system with Amazon SageMaker serverless model customizationManually 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 r→24 Sept 2026Aderant builds intelligent ticket triage with Amazon NovaLearn how Aderant built an intelligent ticket triage system on Amazon Nova Lite through Amazon Bedrock, automating context gathering, classification, routing, and knowledge enrichment for its cloud op→25 Sept 2026Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughputLearn how to scale Mixture-of-Experts (MoE) reinforcement learning on Amazon EKS using Elastic Fabric Adapter (EFA) and DeepEP. This post presents an architecture that combines Amazon EKS, EFA, and Am→25 Sept 2026Accelerate multimodal RL training with SkyRL on Amazon SageMaker HyperPodLearn how to run SkyRL, an open-source reinforcement learning framework, on Amazon SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO. This walkthrough covers building the →1 Oct 2026How uniopen customized Amazon Nova to their retail moderation policies for production deploymentSee how uniopen, a retail platform from Taiwan's Uni-President Enterprises Group, adapted Amazon Nova 2 Lite to its content-moderation policies using supervised fine-tuning in Amazon SageMaker AI and →2 Oct 2026Fine-tune a search agent with multi-turn RL on Amazon SageMaker AIFine-tuning teaches a small search agent your tools and environment, giving it the reliability of a frontier model at lower latency and cost. In this post, we fine-tune an LLM-powered search agent wit
TechniqueMultimodal8 recent entries4 Sept 2026Deploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCoreLearn how to deploy a multimodal WhatsApp ordering assistant that takes customer orders through text, voice notes, and real-time voice calls on a single business number, built on Amazon Bedrock AgentC→9 Sept 2026Simplify and support your TorchServe workloads using Ray Serve Deep Learning ContainersTorchServe is no longer maintained, leaving teams to own the entire GPU inference stack. The AWS Ray Serve Deep Learning Container is a supported, pre-tested container with the framework, GPU drivers,→10 Sept 2026Video and image search in Amazon Bedrock Knowledge Base using Marengo 3.0TwelveLabs Marengo Embed 3.0 is now generally available as an embedding model in Amazon Bedrock Knowledge Bases, bringing fully managed natural language search to video, image, and audio content. This→22 Sept 2026Extending public sector intelligence with Agentforce and AWSPublic sector agencies process large volumes of unstructured evidence, such as body camera footage and scanned documents. This post shows how to combine Amazon Bedrock Data Automation with the Model C→25 Sept 2026Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughputLearn how to scale Mixture-of-Experts (MoE) reinforcement learning on Amazon EKS using Elastic Fabric Adapter (EFA) and DeepEP. This post presents an architecture that combines Amazon EKS, EFA, and Am→25 Sept 2026Accelerate multimodal RL training with SkyRL on Amazon SageMaker HyperPodLearn how to run SkyRL, an open-source reinforcement learning framework, on Amazon SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO. This walkthrough covers building the →29 Sept 2026How Condé Nast built multimodal video discovery with Amazon BedrockCondé Nast's editorial teams spent an average of 250 minutes per task searching a library of more than 140,000 videos using only titles and descriptions. Working with the AWS Generative AI Innovation →6 Oct 2026Best practices for Amazon SageMaker HyperPod administration and governanceLearn how to administer Amazon SageMaker HyperPod through Amazon SageMaker Unified Studio while preserving cluster governance. This post shows platform teams how to design infrastructure boundaries, g
TechniqueSafety8 recent entries17 Sept 2026A shared agentic platform for Wood Mackenzie, on Amazon Bedrock AgentCoreWood Mackenzie built APEX, a shared agentic AI platform on Amazon Bedrock AgentCore so every team can ship production agents without rebuilding runtime, identity, observability, and guardrails from sc→22 Sept 2026How Tata Elxsi detects industrial safety risks in seconds on AWSLearn how Tata Elxsi built IRIS, a real-time industrial safety platform on AWS. IRIS filters camera video at the edge, streams metadata through Amazon Kinesis, runs computer vision on Amazon SageMaker→24 Sept 2026Speaker-labeled transcription with WhisperX on SageMaker AIThe AWS WhisperX Deep Learning Container packages Whisper, wav2vec2 forced alignment, and speaker diarization into a GPU-ready image. Learn how to deploy it to Amazon SageMaker AI real-time and asynch→30 Sept 2026Query claims in natural language with Amazon Bedrock Knowledge BasesThis technical how-to builds a conversational claims assistant on Amazon Bedrock Knowledge Bases that answers natural-language questions with citations. It covers ingesting claim documents from Amazon→6 Oct 2026Responsible AI governance: How AWS positions customers to align with ISO/IEC 42005:2025AWS invests in tools that help customers align with international standards for responsible AI governance. In this post, we explore the AI system impact assessment: what it is, how it improves enterpr→6 Oct 2026Build a voice travel concierge with Amazon Bedrock AgentCore, Managed Knowledge Base and Nova SonicAdd a voice travel concierge to an airline app with Amazon Bedrock AgentCore, Amazon Nova Sonic for real-time speech, and Amazon Bedrock Knowledge Bases for policy answers. Travelers change seats, che→7 Oct 2026How Qlik built grounded, enterprise-scale AI with Amazon BedrockQlik built Qlik Answers on Amazon Bedrock to give its 40,000+ customers grounded, sourced answers across structured and unstructured enterprise data. Learn how a layered, multi-agent architecture with→8 Oct 2026Share GPU clusters across teams with isolation and fairness using Amazon SageMaker HyperPodA reference architecture for securely sharing one Amazon SageMaker HyperPod EKS cluster across multiple teams, using AWS IAM Identity Center for authentication, per-team SageMaker Domains and Kubernet