How TReNDS automates root-cause analysis with Amazon Bedrock
TReNDS, a research center at Georgia State University, built an agentic AI pipeline on Amazon Bedrock and the open-source Strands Agents SDK that automatically investigates production errors in real time, reducing root-cause analysis from 15 to 30 minutes of manual work to under 60 seconds.
The TReNDS Center at Georgia State University, a joint center of Georgia State University, Georgia Institute of Technology, and Emory University, has developed an automated root-cause analysis system using Amazon Web Services (AWS) and Amazon Bedrock. The team uses Amazon CloudWatch subscription filters to detect error-level patterns in logs sent from their applications running on Amazon Elastic Kubernetes Service (Amazon EKS).
When an error is detected, a Lambda function is triggered to run a Strands Agent powered by Amazon Bedrock. This agent investigates the error by pulling surrounding log context, reading source code from GitHub, and producing a structured analysis. The architecture combines CloudWatch subscription filters, AWS Lambda, Strands Agents SDK, and Amazon Bedrock to automate the root-cause investigation process.
The use of Amazon Bedrock allows for AI-powered root-cause analysis without sending data to external endpoints, ensuring data residency and compliance with HIPAA requirements for health-related research data.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
