I Built an AWS DevOps AI Agent Using Kiro Crew + MCP

Описание и применение

Автоматический агент Kiro Crew, использующий AWS DevOps Agent через MCP, обнаруживает и устраняет проблемы в ECS, CodeBuild, CodePipeline и Lambda за 5‑7 минут, снижая MTTR и устраняя беззвучные сбои.

Задача

Silent failures in AWS services (ECS, CodeBuild, CodePipeline, Lambda) that never trigger alarms, leading to prolonged MTTR and resource waste.

Результат

Automated detection and remediation reduced MTTR from 1‑3 hours to 5‑7 minutes, eliminated silent compute waste, and provided audit trails for every incident.

Рабочий процесс

• Configure Kiro Crew MCP server for AWS DevOps Agent
• Set up a cron job to run every 30 minutes
• Kiro Crew spawns 5 parallel subagents to check ECS, CI/CD, CloudWatch, DevOps Agent, and Lambda
• DevOps Agent performs root‑cause analysis and generates mitigation plan
• Kiro Crew executes fixes or opens a PR for human approval
• Kiro Crew verifies service health and logs actions

Доказательства

Kiro Crew agent was awake. It spawned 5 parallel investigations, called AWS DevOps Agent for a health assessment, found the root cause across ECS, CodeBuild, CodePipeline, and Lambda, and flagged everything with severity‑prioritized fixes. By 3:24 AM, done.

Источник

The architecture diagram shows Kiro Crew orchestrating DevOps Agent and executing fixes.

Источник