AWS Machine Learning Blog
Category: HAQM Bedrock
GuardianGamer scales family-safe cloud gaming with AWS
In this post, we share how GuardianGamer uses AWS services including HAQM Nova and HAQM Bedrock to deliver a scalable and efficient supervision platform. The team uses HAQM Nova for intelligent narrative generation to provide parents with meaningful insights into their children’s gaming activities and social interactions, while maintaining a non-intrusive approach to monitoring.
Optimize query responses with user feedback using HAQM Bedrock embedding and few-shot prompting
This post demonstrates how HAQM Bedrock, combined with a user feedback dataset and few-shot prompting, can refine responses for higher user satisfaction. By using HAQM Titan Text Embeddings v2, we demonstrate a statistically significant improvement in response quality, making it a valuable tool for applications seeking accurate and personalized responses.
Integrate HAQM Bedrock Agents with Slack
In this post, we present a solution to incorporate HAQM Bedrock Agents in your Slack workspace. We guide you through configuring a Slack workspace, deploying integration components in HAQM Web Services, and using this solution.
Secure distributed logging in scalable multi-account deployments using HAQM Bedrock and LangChain
In this post, we present a solution for securing distributed logging multi-account deployments using HAQM Bedrock and LangChain.
Build a domain‐aware data preprocessing pipeline: A multi‐agent collaboration approach
In this post, we introduce a multi-agent collaboration pipeline for processing unstructured insurance data using HAQM Bedrock, featuring specialized agents for classification, conversion, and metadata extraction. We demonstrate how this domain-aware approach transforms diverse data formats like claims documents, videos, and audio files into metadata-rich outputs that enable fraud detection, customer 360-degree views, and advanced analytics.
Automating complex document processing: How Onity Group built an intelligent solution using HAQM Bedrock
In this post, we explore how Onity Group, a financial services company specializing in mortgage servicing and origination, transformed their document processing capabilities using HAQM Bedrock and other AWS services. The solution helped Onity achieve a 50% reduction in document extraction costs while improving overall accuracy by 20% compared to their previous OCR and AI/ML solution.
HERE Technologies boosts developer productivity with new generative AI-powered coding assistant
HERE collaborated with the GenAIIC. Our joint mission was to create an intelligent AI coding assistant that could provide explanations and executable code solutions in response to users’ natural language queries. The requirement was to build a scalable system that could translate natural language questions into HTML code with embedded JavaScript, ready for immediate rendering as an interactive map that users can see on screen.
Detect hallucinations for RAG-based systems
This post walks you through how to create a basic hallucination detection system for RAG-based applications. We also weigh the pros and cons of different methods in terms of accuracy, precision, recall, and cost.
Vxceed secures transport operations with HAQM Bedrock
AWS partnered with Vxceed to support their AI strategy, resulting in the development of LimoConnect Q, an innovative ground transportation management solution. Using AWS services including HAQM Bedrock and Lambda, Vxceed successfully built a secure, AI-powered solution that streamlines trip booking and document processing.
Securing HAQM Bedrock Agents: A guide to safeguarding against indirect prompt injections
Generative AI tools have transformed how we work, create, and process information. At HAQM Web Services (AWS), security is our top priority. Therefore, HAQM Bedrock provides comprehensive security controls and best practices to help protect your applications and data. In this post, we explore the security measures and practical strategies provided by HAQM Bedrock Agents to safeguard your AI interactions against indirect prompt injections, making sure that your applications remain both secure and reliable.