Practice
How AI actually ships: enterprise case studies, engineering lessons from production, adoption data and ROI evidence.
How AI actually ships: enterprise case studies, engineering lessons from production, adoption data and ROI evidence.
Latest in Practice
30 stories
ICYMI: What landed for AI builders in August 2026
A recap of August 2026 launches for AI builders across Amazon Bedrock, Amazon Bedrock AgentCore, and Strands: million-token context for OpenAI models, cross-Reg…

Google is a Leader in the 2026 Gartner® Magic Quadrant™ for Enterprise AI Assistants
We are excited to share that Gartner has named Google a Leader in its inaugural 2026 Magic Quadrant for Enterprise AI Assistants. In this comprehensive evaluati…

How Heurist Finance built an AI-native investment workbench on Amazon Bedrock AgentCore
Learn how Heurist built Heurist Finance, a conversational AI investment workbench, on Amazon Bedrock AgentCore. This customer story shows how AgentCore payments…
Building profitable EVs: Ten structural design moves to cut material costs
With incentives declining and input costs rising, electric vehicle profitability is under pressure. Targeted design levers can reduce material costs by 10 to 25…

Automate user-level custom permissions for Amazon Quick
Amazon Quick custom permissions let you enforce least-privilege access by toggling features per user. This post walks through four patterns to automate custom p…

Simplify and support your TorchServe workloads using Ray Serve Deep Learning Containers
TorchServe is no longer maintained, leaving teams to own the entire GPU inference stack.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 co…

How Airtel delivered its flawless Indian Premiere League 2026 cricket broadcasts
For the millions of fervent fans of the Indian Premiere League (IPL), being able to count on a flawless live streaming cricket experience is never up for debate…
The key to AI value is hiding in plain sight: Your operating model
New research shows that organizations undergoing AI transformation succeed not by adopting one “best” operating model, but by making intentional design choices …

Take on your most ambitious work with GPT-6 Astra on Amazon Bedrock
GPT-6 Astra from OpenAI is now generally available on Amazon Bedrock. It brings deeper reasoning and sharper judgment to your most demanding tasks, running on t…

Pathway’s brain-inspired architecture development on Amazon SageMaker HyperPod
Pathway's Baby Dragon Hatchling (BDH) is a brain-inspired, post-transformer architecture that reasons in latent space instead of emitting chain-of-thought token…
Your budget is killing your strategy: four imperatives for CFOs
The traditional annual budget process is broken. It is rigid, backward-looking, and not operationally fit to keep up with today's fast-moving markets. Top-perfo…

Amazon SageMaker Feature Store introduces UpdateRecord for feature-level writes
Amazon SageMaker Feature Store now supports feature-level writes. With the new UpdateRecord API, you can update one or more feature values in a single call with…

Govern models with MLflow and Amazon SageMaker AI Model Registry sync: Part 1
Managed MLflow on Amazon SageMaker AI now syncs richer model metadata (training metrics, evaluation results, inference specs, and lineage) into the SageMaker AI…

Govern models with MLflow and Amazon SageMaker AI Model Registry sync: Part 2
Governing models across accounts is the next step after automatic model registration. This post extends managed MLflow and Amazon SageMaker AI Model Registry sy…
Creating value from AI and digital capabilities in logistics operations
As AI and digital capabilities become more widely adopted in logistics operations, the companies seeing returns from their investments are doing three things di…

How KDDI built Buffmee, a faster, reliable consumer RAG app
When building consumer-facing generative AI applications, balancing high generation quality with fast response times across diverse media types, can be challeng…

How DiDi built intelligent contact center QA with Amazon Bedrock
DiDi built a transparent, self-owned contact center quality assurance (QA) system on Amazon Bedrock, replacing an opaque third-party tool. Intent verification a…

How HPE Zerto built an agentic troubleshooting system with Amazon Bedrock
HPE Zerto built an agentic troubleshooting system powered by Amazon Bedrock that runs on-premises inside the customer environment. This post describes the multi…

Benchmarking small LLM inference on SageMaker AI: G7 vs G5 and G6
Benchmark two 30B Mixture-of-Experts models, Qwen3-Coder-30B and NVIDIA Nemotron-3-Nano-30B, across G5, G6, G6e, and G7 GPU instances on Amazon SageMaker AI. Co…

Automated agent evaluation with Amazon Bedrock AgentCore and GitHub Actions
Wire Amazon Bedrock AgentCore Evaluations into a GitHub Actions pipeline: deploy an AI agent and an OAuth-protected MCP server to AgentCore runtime, invoke the …
Modernizing for the mission: An interview with Jamie Wolff
The National Nuclear Security Administration’s CIO shares that modernization means rebuilding infrastructure, data, and talent at once—while keeping the mission…
Global Farmer Insights 2026
Our biennial global survey of 5,500 farmers finds that they are becoming selective in their spending in the face of economic pressures. AI is making inroads, ev…

Welcome Alex Kurland, Menlo’s Newest Partner
Today is a big day for Menlo as we welcome Alex Kurland to the team! Adding a partner to a close-knit partnership is a big deal in many ways, but this is partic…
Smart rail infrastructure: Laying the digital tracks for resilient networks
Adopting digital and AI advances can help rail infrastructure technology address long-standing challenges. Where should operators prioritize?…
GS Caltex’s Saehong Hur: Leading from the top; moving forward—together
For Saehong Hur, continued communication and an integrated mindset are vital for adapting to changing market needs and maximizing value.…

Deploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCore
Learn how to deploy a multimodal WhatsApp ordering assistant that takes customer orders through text, voice notes, and real-time voice calls on a single busines…

Designing lifecycle policies for AgentCore memory
Long-running AI agents accumulate outdated memories that degrade quality and create compliance risk. Learn how to design memory lifecycle policies for Amazon Be…

Spanner migrations: Automating dual-write with Antigravity CLI for minimal disruption
When Google's Finance Engineering team needed to modernize their legacy data layer, they chose Spanner, a globally distributed, strongly consistent, multi-model…

How Intuit built an agentic disaster recovery assistant with Amazon Bedrock
Disaster recovery at scale is hard. Learn how Intuit built EWOK Agent, an agentic disaster recovery assistant on Amazon Bedrock that lets on-call engineers run …

Customizing your knowledge base on Amazon Bedrock for large and complex documents using Amazon Textract
Learn how to customize an Amazon Bedrock knowledge base for large, complex documents by combining the high-accuracy text extraction of Amazon Textract with the …