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

Описание и применение

Автономный агент Kiro Crew + AWS DevOps Agent обнаруживает и устраняет проблемы в ECS, CodeBuild и Lambda за 7 минут, снижая MTTR до 5‑7 минут и устраняя беззвучные сбои.

Задача

Silent failures in AWS services (ECS, CodeBuild, Lambda) go unnoticed because no alarms are set, leading to prolonged MTTR and resource waste.

Результат

Automated incident response reduced MTTR from 1‑3 hours to 5‑7 minutes, eliminated silent failures, and saved compute costs.

Рабочий процесс

• Configure Kiro Crew MCP server for AWS DevOps Agent
• Set a cron job to run every 30 minutes
• Kiro Crew spawns parallel subagents for ECS, CI/CD, CloudWatch, DevOps Agent, Lambda checks
• DevOps Agent performs root‑cause analysis and generates mitigation plan
• Kiro Crew executes fixes or opens PRs for approval
• Verify service health and log results

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