Practice

ScienceSoft’s HIPAA-compliant AI voice scheduler built on AWS

In this post, you will learn how ScienceSoft, an Amazon Web Services (AWS) Services Partner, integrated Amazon Nova 2 Sonic with Amazon Bedrock Guardrails to bu…

Scaling medical content review at Flo Health with Amazon Bedrock – Part 2

In this post, we share how Flo Health’s engineering team turned a proof of concept (PoC) from the AWS Generative AI Innovation Center into a production-grade, A…

Rewiring customer experience for the agentic era

As AI agents take on moment-to-moment decisions, leading companies are redesigning customer experience from predefined journeys to dynamic, cross-channel orches…

Building expertise in the age of AI: Who trains the next generation?

As AI reshapes entry-level work, organizations should rethink how expertise is developed by integrating knowledge management, role design, learning, and coachin…

Is that AI agent worth it? Agentic economics and the modern operating model

As companies focus on spiraling AI costs, they need to make sure not to lose sight of the real prize.…

OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock

Today, GPT-5.6 Sol, Terra, and Luna from OpenAI are generally available on Amazon Bedrock, bringing the smartest family of models from OpenAI yet to Amazon Bedr…

Building Service Topology at Scale: Architecture, Challenges, and Lessons Learned

How a 180-year-old news institution prepares for its next reinvention

Associated Press CEO Daisy Veerasingham discusses AI, the economics of trusted content, and why preserving editorial independence matters more than preserving a…

Launching UI for generative AI inference recommendations in Amazon SageMaker AI

In this post, we introduce the UI for optimized generative AI inference recommendations in Amazon SageMaker AI Studio, a low-code no-code (LCNC) experience. The…

Implement on-behalf-of token exchange for multi-tenant agents with Amazon Bedrock AgentCore Gateway

Building multi-tenant agents with Amazon Bedrock AgentCore and Apply fine-grained access control with Bedrock AgentCore Gateway interceptors establish the conce…

Building an agentic AI solution at Bluesight with Amazon Bedrock

In this post, we describe how Bluesight used two AWS engagements and Amazon Bedrock AgentCore to evolve from a single-product AI prototype to Prism, a unified a…

When your brain works differently, AI isn’t a luxury—it’s accessibility

In this post, I share how AI serves as an accessibility tool for neurodivergent professionals. The system is built on Amazon Quick on your desktop, an AI-powere…

Securing the AI supply chain on GKE: Introducing k8s-aibom for automated AI BOMs

How should your security team manage shadow AI? Workloads deployed by developers without formal registration can often evade traditional security scanners, beca…

How AI is reshaping value creation in residential real estate

McKinsey’s Alex Wolkomir discusses how housing leaders can win with AI by improving customer experiences, redesigning workflows, and building trust between part…

Rewired takes: Practical people lessons for scaling AI adoption

McKinsey Senior Partner Brooke Weddle explores how companies are successfully scaling their AI programs.…

Climate planning has prioritized floods. Heat demands equal attention

Summer in the Northern Hemisphere has gotten off to a very hot start. Europe has baked under record-breaking temperatures, while a “heat dome” blankets much of …

Building a more resilient industrial base may require $2 trillion in investment

As the United States approaches its 250th anniversary, intensifying technological competition and geopolitical risks have resurfaced a decades-old question with…

Frontier and Center: Who evaluates the evaluations?

Editor’s note: Some of the most interesting questions in AI are being asked by information theoreticians, around how to provide context to an emerging class of …

Fine-tune NVIDIA Nemotron 3 models with Amazon SageMaker AI serverless model customization

In this post, we explore what makes the Nemotron 3 architecture unique, walk through the fine-tuning techniques available, and show you step-by-step how to get …

Disaggregated prefill and decode for LLM inference on SageMaker HyperPod

In this post, we show how to implement DPD with vLLM on Amazon SageMaker HyperPod using the HyperPod Inference Operator.…

How KTern.AI built agentic AI for SAP on Amazon Bedrock AgentCore

Evolving from a traditional software as a service (SaaS) platform into a next-generation agentic AI platform meant orchestrating multiple specialized agents acr…

Deploying quantized models on Amazon SageMaker AI with Unsloth

In this post, you will learn four deployment patterns for taking models that have already been quantized with Unsloth and deploying them on AWS infrastructure. …

Scaling agentic workflows with native case management in Amazon Quick Automate

In this post, we show you how to combine case management with agentic automation capabilities in Quick Automate. We introduce case management and explore the li…

Build a semantic layer for agentic AI on AWS with Stardog and Amazon Bedrock AgentCore

In this post we show how to build a semantic layer on AWS using Stardog’s Semantic AI Application over Amazon Aurora and Amazon Redshift, and how to run a Stran…

Real-time dental image verification with Amazon SageMaker AI at Henry Schein One

This post describes how Henry Schein One closed that gap by building Image Verify, an AI-powered quality verification system on Amazon SageMaker AI that evaluat…

AI in five industries: What’s now, and what’s next

The headlines are everywhere. The nuance is more elusive. In these video Explainers, McKinsey partners go sector by sector to parse what’s happening with AI now…

Author Talks: In Hollywood and in business, it’s cool to be kind

In Lead with Kindness, television writer and producer Melinda Hsu explores how so-called soft skills like empathy, mindfulness, and collaboration can result in …

The real AI advantage

The next wave of value from AI will flow to those leaders who redesign business models, eliminate friction, and build organizations that learn faster than the c…

Enhancing enterprise inference on Amazon SageMaker HyperPod with data capture, Hugging Face, NVMe, and Route 53 integration

In this post, we walk through five capabilities now available in SageMaker HyperPod inference: multi-tier data capture for auditing and model improvement, direc…

MCP tool design: Practical approaches and tradeoffs

In this post, we show where MCP tool design goes wrong and how to fix it with practical context engineering approaches.…