Prompting for the best price-performance
In the drive to remain competitive, businesses today are turning to AI to help them minimize cost and maximize efficiency. It’s incumbent on them to find the most suitable AI model—the one that will help them achieve more while spending less. For many businesses, the migration from OpenAI’s model family to Amazon Nova represents not […]
Evaluate models or RAG systems using Amazon Bedrock Evaluations – Now generally available
Organizations deploying generative AI applications need robust ways to evaluate their performance and reliability. When we launched LLM-as-a-judge (LLMaJ) and Retrieval Augmented Generation (RAG) evaluation capabilities in public preview at AWS re:Invent 2024, customers used them to assess their foundation models (FMs) and generative AI applications, but asked for more flexibility beyond Amazon Bedrock models […]
Fine-tune large language models with reinforcement learning from human or AI feedback
Large language models (LLMs) can be used to perform natural language processing (NLP) tasks ranging from simple dialogues and information retrieval tasks, to more complex reasoning tasks such as summarization and decision-making. Prompt engineering and supervised fine-tuning, which use instructions and examples demonstrating the desired task, can make LLMs better at following human intents, in […]
How Lumi streamlines loan approvals with Amazon SageMaker AI
This post is co-written with Paul Pagnan from Lumi. Lumi is a leading Australian fintech lender empowering small businesses with fast, flexible, and transparent funding solutions. They use real-time data and machine learning (ML) to offer customized loans that fuel sustainable growth and solve the challenges of accessing capital. Their goal is to provide fast […]
How AWS Sales uses generative AI to streamline account planning
Every year, AWS Sales personnel draft in-depth, forward looking strategy documents for established AWS customers. These documents help the AWS Sales team to align with our customer growth strategy and to collaborate with the entire sales team on long-term growth ideas for AWS customers. These documents are internally called account plans (APs). In 2024, this […]
Shaping the future: OMRON’s data-driven journey with AWS
This post is co-written with Emrah Kaya and Xinyi Zhou from Omron Europe. Data is one of the most critical assets of many organizations. They’re constantly seeking ways to use their vast amounts of information to gain competitive advantages. OMRON Corporation is a leading technology provider in industrial automation, healthcare, and electronic components. In their […]
AI Workforce: using AI and Drones to simplify infrastructure inspections
Inspecting wind turbines, power lines, 5G towers, and pipelines is a tough job. It’s often dangerous, time-consuming, and prone to human error. That’s why we at Amazon Web Services (AWS) are working on AI Workforce—a system that uses drones and AI to make these inspections safer, faster, and more accurate. This post is the first […]
Ray jobs on Amazon SageMaker HyperPod: scalable and resilient distributed AI
Foundation model (FM) training and inference has led to a significant increase in computational needs across the industry. These models require massive amounts of accelerated compute to train and operate effectively, pushing the boundaries of traditional computing infrastructure. They require efficient systems for distributing workloads across multiple GPU accelerated servers, and optimizing developer velocity as […]
Using Large Language Models on Amazon Bedrock for multi-step task execution
The goal of this blog post is to show you how a large language model (LLM) can be used to perform tasks that require multi-step dynamic reasoning and execution. Examples of tasks that require dynamic reasoning and execution are answering questions of the form “What is the average length of stay for patients with [specific […]
Introducing AWS MCP Servers for code assistants (Part 1)
We’re excited to announce the open source release of AWS MCP Servers for code assistants — a suite of specialized Model Context Protocol (MCP) servers that bring Amazon Web Services (AWS) best practices directly to your development workflow. Our specialized AWS MCP servers combine deep AWS knowledge with agentic AI capabilities to accelerate development across […]