Home icon

How Amazon Finance built an AI assistant using Amazon Bedrock and Amazon Kendra to support analysts for data discovery and business insights

Machine Learning Blog



Amazon Finance developed an AI-powered assistant using Amazon Bedrock and Amazon Kendra to help financial analysts discover data and gain business insights more efficiently. The solution addresses key challenges in financial planning and analysis by enabling natural language queries across complex data sources.

  • Uses Anthropic's Claude 3 Sonnet model and Amazon Kendra for intelligent search
  • Dramatically reduced search time by 30% and improved search result accuracy by 80%
  • Enables analysts to find information in 5-10 minutes compared to 45-60 minutes previously
  • Achieved 83% precision and 88% faithfulness in knowledge searches
  • 92% of analysts prefer this new system over traditional search methods

The solution transforms how finance professionals interact with complex data by providing a conversational, context-aware search experience that improves productivity and decision-making.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Dec 2
2024
How Amazon Finance Automation built a generative AI Q&A chat assistant using Amazon Bedrock
May 28
2025
Part 3: Building an AI-powered assistant for investment research with multi-agent collaboration in Amazon Bedrock and Amazon Bedrock Data Automation
May 2
2025
Build a gen AI–powered financial assistant with Amazon Bedrock multi-agent collaboration
Jun 26
2024
AI-powered assistants for investment research with multi-modal data: An application of Amazon Bedrock Agents

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.