aws-solutions-library-samples

Eks Troubleshooting Agentic AI Chatops — AI skill for Claude Code

AI community

This Guidance demonstrates how to address the complexity of troubleshooting Amazon EKS environments with multiple metrics and logs by implementing an agentic AI workflow that uses generative AI with R.

How to install Eks Troubleshooting Agentic AI Chatops

This entry records only its repository, not the path inside it, so there is no exact command to give. Open aws-solutions-library-samples/eks-troubleshooting-agentic-ai-chatops and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Eks Troubleshooting Agentic AI Chatops does

Alternatives in AI

Ccstatusline — by sirmalloc - A highly customizable status line formatter for Claude Code CLI that displays model info, git b 5.5k ★
Generative Media Skills — Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI) 3k ★
Gtm Engineer Skills — Claude Code skill for improving website AEO (AI Engine Optimization) and GEO (Generative Engine Optimization) 761 ★

README

NOTE: for sample code for this [AWS Blog](https://aws.amazon.com/blogs/architecture/architecting-conversational-observability-for-cloud-applications/) please use the [code branch](https://github.com/aws-solutions-library-samples/eks-troubleshooting-agentic-ai-chatops/tree/blog) from this repository. This code branch is updated and is related to the AWS guidance below.

Guidance for Troubleshooting of Amazon EKS using Agentic AI workflow on AWS

This guidance provides an example of Platform Engineering approach to troubleshooting Amazon EKS (Elastic Kubernetes Service) issues using Agentic AI workflow integrated with ChatOps via Slack

**Strands-based AI Agentic workflow Troubleshooting**: An intelligent agent using AWS [Strands Agent framework](http://strandsagents.com/latest/) with [EKS MCP server](https://awslabs.github.io/mcp/servers/eks-mcp-server) integration for real-time troubleshooting

It can be deployed using [Terraform](https://developer.hashicorp.com/terraform), which provisions all necessary AWS resources including EKS cluster with compute plane, required add-ons, monitoring tools, and the agentic troubleshooting agent.

Architecture

Reference Architecture - EKS Cluster

![Reference Architecture Diagram](/static/images/EKS%20troubleshooting%20agentic%20AI%20diagram%201.png)

_Figure 1: Guidance for Troubleshooting of Amazon EKS using Agentic AI workflow on AWS - Reference Architecture_

Reference Architecture Steps

**Amazon EKS Cluster**: Managed Kubernetes control plane and worker nodes running containerized workloads, providing the foundation for the agentic troubleshooting system.
**Agentic Troubleshooting Agent**: Strands-based multi-agent system deployed as pods in the EKS cluster, orchestrating intelligent troubleshooting workflows through specialized agents.
**Amazon Bedrock Integration**: Provides foundational AI models (Claude for analysis, Titan Embeddings for semantic search) for natural language processing and int