AWS

2026-09-14

MODELS · 1 SOURCE · AWS Machine Learning

AWS presents an 8-step framework for generative AI customization, from prompts to custom models

AWS Machine Learning published an article offering an 8-step decision framework to help pick generative AI customization approaches on AWS, covering prompt engineering, RAG, fine-tuning, continued pre-training and Amazon Nova Forge, with the recommendation to start simple and escalate only when necessary.

6.0

2026-09-11

CODING · 1 SOURCE · AWS Machine Learning

Monitoring production agent lifecycle with Amazon Bedrock AgentCore Evaluations and AWS DevOps Agent

An AWS Machine Learning blog post outlines a dual-layer monitoring approach for production multi-agent systems: Amazon Bedrock AgentCore Evaluations for continuous quality scoring of agents, and the AWS DevOps Agent for autonomous investigation of infrastructure issues. The approach is demonstrated on a four-agent airline reservation system.

6.0

2026-09-10

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon SageMaker Inference adds prefix-aware routing to reduce LLM latency

Amazon SageMaker Inference now offers prefix-aware routing, a strategy that sends requests sharing the same prompt prefix to the same instance so the KV cache stays warm. In benchmarks on Llama 3.1 70B, this reduced P50 time-to-first-token by up to 77% and increased KV cache hit rates from about 25% to over 80%.

7.0

2026-09-10

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon SageMaker HyperPod adds model caching to reduce inference cold starts

Amazon SageMaker HyperPod now supports model caching for inference: model weights and container images can be pre-loaded onto cluster nodes' local NVMe storage so pods read from local disk instead of downloading over the network. AWS says this cuts cold starts from tens of minutes to seconds; the announcement explains how it works and how to enable it.

7.0

2026-09-10

MODELS · 1 SOURCE · AWS Machine Learning

AvioBook prototypes Connected Analytics on Amazon Bedrock AgentCore to explain turnaround delays

AvioBook, a Thales Group company, prototyped a Connected Analytics solution using Amazon Bedrock AgentCore to convert AvioBook Connect operational data into plain-language, evidence-based answers for airline managers and dispatchers. The prototype is intended to help users identify and act on causes of flight turnaround delays.

4.0