Getting insights from Amazon Managed Service for Prometheus using natural language powered by Amazon Bedrock
AWS Cloud Operations Blog
This article discusses how to use Amazon Bedrock, a generative AI service, to get insights from application and infrastructure metrics stored in Amazon Managed Service for Prometheus using natural language queries, without having to write complex PromQL queries.
Specifically, the article covers:
- Setting up monitoring for an Amazon EKS cluster using AWS Managed Collector and Amazon Managed Service for Prometheus
- Configuring a Lambda function as an action group for the Amazon Bedrock agent
- Creating an Amazon Bedrock agent and associating it with the Lambda function and a knowledge base
- Using the Bedrock agent to ask natural language questions about cluster health, resource utilization, and troubleshooting
- Cleaning up the resources created for the demo
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
Sep 18
2024
2024
Automating metrics collection on Amazon EKS with Amazon Managed Service for Prometheus managed scrapers
May 22
2025
2025
Amazon Managed Service for Prometheus launches query insights and control capabilities
Aug 8
2024
2024
Analyze blockchain data with natural language using Amazon Bedrock
Oct 2
2024
2024
Amazon Managed Service for Prometheus now supports Internet Protocol Version 6 (IPv6)
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.