Gain access to AWS Expenditure and Utilization perspectives using innovative AI enhanced by Amazon Bedrock | AWS Machine Learning Blog

Overview

Managing cloud costs and understanding resource usage can be a challenging task, especially for organizations with complex AWS deployments. AWS Cost and Usage Reports (AWS CUR) provide valuable data insights, but interpreting and querying the raw data can be complex.

Solution using Generative AI and Amazon Bedrock

This post explores a solution that utilizes generative artificial intelligence (AI) to simplify the querying process of CUR data stored in an Amazon Athena database. By generating SQL queries from users’ natural language questions, running them on Athena, and presenting the results on a web portal, the solution aims to streamline the analysis of AWS cost and usage data.

Challenges and Benefits

Various challenges can hinder organizations from effectively analyzing their CUR data, leading to inefficiencies, overspending, and missed optimization opportunities. By leveraging generative AI with Amazon Bedrock, this solution aims to address and simplify these challenges. The AWS CUR chatbot solution empowers users to ask questions in natural language, facilitating a deeper understanding of AWS costs and resource usage.

Architecture and Steps

The solution uses Amazon Bedrock, offering a choice of foundation models from leading AI companies. The architecture of the solution involves generating SQL queries, database querying, and presenting results on a user-friendly web interface. Steps to set up the solution are outlined, including prerequisites and precautions to avoid charges.

Conclusion

By enabling users to ask natural language questions and leveraging generative AI, this solution facilitates informed decision-making, optimized cloud spending, and improved resource utilization for organizations. Amazon Bedrock provides a powerful platform to build generative AI applications, empowering users with valuable insights into their AWS costs and usage.