Blog_dumb

This post is co-written with Abhinav Pandey from Nippon Life India Asset Management Ltd. Accurate information retrieval through generative AI-powered assistants is a popular use case for enterprises. To reduce hallucination and improve overall accuracy, Retrieval Augmented Generation (RAG) remains the most commonly used method to retrieve reliable and accurate responses that use enterprise data …

How Nippon India Mutual Fund improved the accuracy of AI assistant responses using advanced RAG methods on Amazon Bedrock Read More »

Drug discovery is a complex, time-intensive process that requires researchers to navigate vast amounts of scientific literature, clinical trial data, and molecular databases. Life science customers like Genentech and AstraZeneca are using AI agents and other generative AI tools to increase the speed of scientific discovery. Builders at these organizations are already using the fully …

Build a drug discovery research assistant using Strands Agents and Amazon Bedrock Read More »

In early 2025, we introduced the Amazon Nova Act SDK as a research preview to help developers build agents that reliably complete tasks in a web browser. Now, we are excited to work with customers to take their agents to production in a limited preview, using new AWS integrations including AWS Identity and Access Management …

Amazon Nova Act SDK (preview): Path to production for browser automation agents Read More »

This post is co-written with Jessie Jiao from Crypto.com. Crypto.com is a crypto exchange and comprehensive trading service serving 140 million users in 90 countries. To improve the service quality of Crypto.com, the firm implemented generative AI-powered assistant services on AWS. Modern AI assistants—artificial intelligence systems designed to interact with users through natural language, answer …

Optimizing enterprise AI assistants: How Crypto.com uses LLM reasoning and feedback for enhanced efficiency Read More »

Building modern serverless applications on AWS requires navigating best practices to manage the integration between multiple services, such as AWS Lambda, Amazon API Gateway, Amazon DynamoDB, and Amazon EventBridge. Security considerations, performance optimization, and implementing a comprehensive monitoring systems adds further requirements to build a serverless architecture while adhering to AWS best practices. Amazon Q Developer CLI with Model Context Protocol …

Build modern serverless solutions following best practices using Amazon Q Developer CLI and MCP Read More »

Legal teams spend bulk of their time manually reviewing documents during eDiscovery. This process involves analyzing electronically stored information across emails, contracts, financial records, and collaboration systems for legal proceedings. This manual approach creates significant bottlenecks: attorneys must identify privileged communications, assess legal risks, extract contractual obligations, and maintain regulatory compliance across thousands of documents …

Build an intelligent eDiscovery solution using Amazon Bedrock Agents Read More »

This post is co-written with Bogdan Arsenie and Nick Mattei from PerformLine. PerformLine operates within the marketing compliance industry, a specialized subset of the broader compliance software market, which includes various compliance solutions like anti-money laundering (AML), know your customer (KYC), and others. Specifically, marketing compliance refers to adhering to regulations and guidelines set by …

How PerformLine uses prompt engineering on Amazon Bedrock to detect compliance violations  Read More »

Cold start in recommendation systems goes beyond just new user or new item problems—it’s the complete absence of personalized signals at launch. When someone first arrives, or when fresh content appears, there’s no behavioral history to tell the engine what they care about, so everyone ends up in broad generic segments. That not only dampens …

Boost cold-start recommendations with vLLM on AWS Trainium Read More »

Large language models (LLMs) have rapidly evolved, becoming integral to applications ranging from conversational AI to complex reasoning tasks. However, as models grow in size and capability, effectively evaluating their performance has become increasingly challenging. Traditional benchmarking metrics like perplexity and BLEU scores often fail to capture the nuances of real-world interactions, making human-aligned evaluation …

Benchmarking Amazon Nova: A comprehensive analysis through MT-Bench and Arena-Hard-Auto Read More »