admin

Improving HCLS AI reasoning with open-source agent skills

Improving HCLS AI reasoning with open-source agent skills

AI agents built on foundation models (FMs) often misapply healthcare and life sciences (HCLS) decision frameworks, even when they’ve seen the guidelines in training and in the system prompt. Ask an agent to classify a TP53 missense variant using ACMG/AMP criteria. It will cite the correct framework but misapply evidence categories, skip population frequency thresholds, […]

Improving HCLS AI reasoning with open-source agent skills Read More »

Fault tolerant distributed training on Amazon EKS using NVRx

Fault tolerant distributed training on Amazon EKS using NVRx

Large-scale distributed training jobs run for hours or days across dozens of nodes. At that scale and duration, interruptions are statistically inevitable: network partitions, memory errors, software exceptions, or infrastructure events will eventually disrupt at least one worker. A single GPU fault triggers a cascade: NVIDIA Collective Communication Library (NCCL) timeouts propagate to healthy workers,

Fault tolerant distributed training on Amazon EKS using NVRx Read More »

Optimizing agent system prompts with Amazon Bedrock AgentCore

Optimizing agent system prompts with Amazon Bedrock AgentCore

In a previous launch post, we introduced AgentCore optimization, a capability of Amazon Bedrock AgentCore that can help you improve the quality of your agents. Improving a low-scoring agent has traditionally been a manual process. You review long traces to find where the agent goes wrong, tune individual components such as prompts, tool descriptions, and

Optimizing agent system prompts with Amazon Bedrock AgentCore Read More »

Build a serverless PII redaction pipeline with Amazon Bedrock Data Automation

Build a serverless PII redaction pipeline with Amazon Bedrock Data Automation

Organizations that process thousands of scanned documents daily, including medical forms, insurance claims, and financial records, face a recurring compliance need: personally identifiable information (PII) redaction before documents are shared with third parties or processed downstream. Manual redaction doesn’t scale: It consumes staff hours, introduces human error, and creates compliance exposure. Redaction is also a

Build a serverless PII redaction pipeline with Amazon Bedrock Data Automation Read More »

Optimizing cost and latency with Amazon Bedrock prompt caching

Optimizing cost and latency with Amazon Bedrock prompt caching

Prompt caching in Amazon Bedrock can reduce your input token costs by up to 90 percent when you repeatedly send the same context to foundation models, based on Amazon Bedrock prompt caching pricing. Without caching, a 10,000-token contract sent alongside 50 user questions means 500,000 input tokens billed at full price for content the model

Optimizing cost and latency with Amazon Bedrock prompt caching Read More »

Build an AI-powered product tagging system with Amazon SageMaker serverless model customization

Build an AI-powered product tagging system with Amazon SageMaker serverless model customization

Retail catalogs rarely arrive as clean, structured attributes. Product names, descriptions, and category paths come from many sources and change continuously. Search, recommendations, and catalog navigation depend on consistent tags, but manually applying those tags across thousands of stock keeping units (SKUs) is slow and difficult to keep consistent. A general-purpose frontier model can generate

Build an AI-powered product tagging system with Amazon SageMaker serverless model customization Read More »

Announcing instance preference lists for Amazon SageMaker AI training jobs

Announcing instance preference lists for Amazon SageMaker AI training jobs

Getting access to the right GPUs when you need them is one of the biggest challenges in training or customizing AI models at scale. During peak demand periods, your preferred GPU may not be immediately available – and when your job is tied to one specific GPU configuration, the only option is to wait or

Announcing instance preference lists for Amazon SageMaker AI training jobs Read More »

Scroll to Top