New in AWS Quick: More capable flows, an updated web experience, and agents that work togetherTurn one person’s process into your team’s process, get more done in the Quick web app, and get more complete answers from agents working together. AWS Quick is the AI workspace built only for work. Today, we are releasing updates that helpAWAWS ML11/21 09:06
Cut self-hosted LLM cost and latency with the distributed KV caching agent skillCustomers increasingly self-host large language models (LLMs) on GPUs for control over cost, accuracy, and latency. However, self-hosting often means paying for redundant GPU work because small, isolated caches on each server can’t hold or AWAWS ML11/21 08:14
Introducing managed cluster extensions for observability and user management in Amazon SageMaker HyperPod SlurmKeeping a shared Slurm cluster for foundation model development in sync entails keeping several separately maintained pieces of configuration matched to what’s running on the nodes. The cluster’s shape lives on multiple configuration files,AWAWS ML11/21 07:07
Introducing Amazon SageMaker HyperPod Global Inference Gateway: One endpoint across Regions and clustersDuring a traffic peak, a request can sit in a queue on a saturated HyperPod cluster while GPUs on another cluster, sometimes in another AWS Region, sit idle. You have already paid for that capacity, but your requests can’t reach it. In IntrAWAWS ML11/21 06:35
How Standard Bank Group automates AI risk assessment for generative AIThis post is co-written with Tala Qraitem from AWS and Jörg Fischer from Standard Bank Group Having an AI policy is one thing. Proving, one use case at a time, that AI systems follow it is another. Every new generative AI application adds oAWAWS ML11/21 04:37
Announcing Amazon Textract Insights: Verifiable generative AI for documentsOrganizations across financial services, insurance, healthcare, and the public sector depend on document processing. They turn scanned files and paper forms into structured data their systems can act on. As generative AI has matured, these AWAWS ML11/21 04:22
Introducing enhanced infrastructure observability in Amazon SageMaker HyperPodLarge-scale model training is one of the most expensive workloads you can run on GPUs, and a single unhealthy accelerator can stall an entire distributed job. When training throughput drops, the hard part is rarely noticing that something iAWAWS ML11/21 02:24
Amazon SageMaker Inference: 2026 launches in review, part 2From first endpoint to global fleet: 14 more launches for managed endpoints and HyperPod Inference In September, Amazon SageMaker Inference: 2026 year-to-date launches in review covered 13 launches that shortened the path from a model to a AWAWS ML11/20 08:34
Use Kimi Code CLI with models on Amazon BedrockKimi Code CLI is an open source coding agent from Moonshot AI, the creator of the Kimi series of open-weight foundation models. Previously, using Kimi Code with models on Amazon Bedrock meant configuring a generic connection “provider” withAWAWS ML11/20 08:33
Enable AI agents to pay for AWS Marketplace x402 products with Amazon Bedrock AgentCore paymentsWhen Amazon Bedrock AgentCore payments became generally available in August 2026, agents could autonomously pay for paid APIs, MCP servers, and web content over open protocols like x402 and MPP with payment limits and full observability. ToAWAWS ML11/20 07:02
How the BMW Group governs hundreds of agents across thousands of developersWhen hundreds of agents serve thousands of developers, enterprise governance can’t be an afterthought. At the BMW Group’s R&D, more than 12,500 developers work on approximately 500 million lines of vehicle software code. This software is auAWAWS ML11/20 06:20
Run your whole selling business in AWS QuickMost sellers do not need another AI product to learn. They need the tools and information they already use brought together, so they can see what is happening in their business and act on it. AWS Quick and the Amazon Selling Partner plugin AWAWS ML11/20 06:16
Amazon SageMaker AI now detects latency drift, idle GPUs, and missed optimizations on your inference endpointsEvery inference endpoint is well tuned the day it goes into production. Teams choose an instance type, serving configuration, and scaling settings that suit the model and its traffic at launch. With the endpoint serving smoothly, they underAWAWS ML11/20 05:28
Inside Amazon Connect Talent: The science of structured AI interviewsFor organizations hiring hundreds or thousands of people, every interview presents the same challenge: How do you give candidates a consistent opportunity to demonstrate their skills while gathering the evidence needed to make informed hiriAWAWS ML11/20 05:23
Amazon Bedrock AgentCore harness adds Strands harness defaults, built-in tools, and lifecycle hooksWhen building an AI agent, selecting a model is only the first step. The agent still needs tools, instructions for finishing the job, a way to manage context growth in long sessions, and guardrails before it executes any consequential actioAWAWS ML11/20 04:01
Amazon Polly launches voice cloning: A unique voice for your brandVoice cloning in Amazon Polly is now generally available as a gated release. Give Amazon Polly a few minutes of audio recordings from a speaker who has agreed to have their voice cloned, and Amazon Polly builds your own cloned voice in thatAWAWS ML11/20 03:53
Optimize AI economics on Amazon Bedrock with Accenture’s sequenced approachAs enterprises scale AI on Amazon Bedrock , token spend often grows even as per-token prices fall. Without cost allocation tags in place, your cloud invoice shows AI spend as a single line item rather than by team, workload, agent, or modelAWAWS ML11/20 02:48
From learning to leaderboard: How Cisco upskilled 1,200 engineers in agentic AI with AWS AI LeagueCisco, like many large engineering organizations, is adopting generative and agentic AI to change how its engineers build software. The hard part is no longer access to the technology. It’s helping thousands of engineers move from watching AWAWS ML11/20 02:26
Keep inference running through regional capacity shortfalls with cross-Region inference routing in Amazon SageMaker AIServing a model from more than one AWS Region is a well-established pattern for highly available inference: when one Region runs short of GPU capacity, requests move to another. The pattern is simple to describe and hard to operate. Until nAWAWS ML11/20 02:20
Protect agent tool calls with Skyflow and Amazon Bedrock AgentCore GatewayIn this post, we show how Skyflow and Amazon Bedrock AgentCore Gateway keep sensitive data out of the tools your AI agents call, and out of the model context those tools feed. We add Skyflow Detect to Amazon Bedrock AgentCore Gateway as a rAWAWS ML11/20 02:14
PolyAI Dialog-RSN-1 is now on Amazon SageMaker JumpStartDialog-RSN-1, a reasoning model built for real-time complex dialog, is available today on AWS Marketplace and Amazon SageMaker JumpStart. It powers frontier dialog: agents that hear a live call, reason about it, and act in real time. As an AWAWS ML11/20 01:28
Using NVIDIA Run:ai GPU Fractioning on Amazon EKSGPU sharing is not new: Multi-Instance GPU (MIG), time-slicing, and Multi-Process Service (MPS) address different isolation and utilization needs. NVIDIA Run:ai GPU Fractioning builds on MPS with Kubernetes-integrated scheduling, per-Pod meAWAWS ML11/20 00:13
Full Fine-Tuning (FFT) on SageMaker AI Serverless Model CustomizationFine-tuning is the process of continuing to train a pretrained large language model (LLM) on a company’s own data so it adapts to a specific domain, task, or style rather than relying on general-purpose knowledge alone. For businesses, the AWAWS ML11/19 08:15
Exa boosts embedding throughput by 50% to index billions of documents on AWS AI chipsAt Exa , we are building one of the few true web indexes by aggregating and serving knowledge from across the web, along with private and synthetic sources. We optimize the index for semantic search, grounding agents and humans in true, higAWAWS ML11/19 07:58
Introducing workload recovery and expanded infrastructure checks on Amazon SageMaker HyperPodLarge training jobs can fail even when every node looks healthy. A GPU with a subtle fault can pass its stress tests and still return wrong values. When a job stalls on an NCCL timeout, it keeps its GPUs, and Slurm still shows it as runningAWAWS ML11/19 07:03
Introducing the Amazon SageMaker JumpStart Model LeaderboardAmazon SageMaker JumpStart gives you hundreds of open-weight foundation models you can deploy quickly. That choice is powerful, but it also creates a real question: Which model should you start with? Comparing models usually means reading mAWAWS ML11/19 06:31
How Airbnb uses cost per task to operate coding agents on Amazon BedrockAmazon Bedrock provides access to foundation models from multiple providers through a common API, with AWS managing the model infrastructure. It integrates with AWS access controls and monitoring, and processes prompts, code, and model respAWAWS ML11/19 05:48