AWS Announces General Availability of DevOps Agent for Automated Incident Investigation

2026-04-18 · Source: InfoQ · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure, Software Development & Engineering · Depth: Intermediate, short

Summary

AWS has announced the general availability of DevOps Agent, a generative AI-powered assistant designed to automate incident investigation and operational tasks across AWS, Azure, and on-prem environments. Introduced at re:Invent 2025 and built on Amazon Bedrock AgentCore, the agent integrates with observability tools, runbooks, code repositories, and CI/CD pipelines to correlate telemetry, code, and deployment data. It autonomously triages issues, speeds up resolution, and identifies patterns to prevent future outages. Key improvements include support for custom agent skills and custom charts/reports. Early preview numbers showed up to 75% lower Mean Time To Resolution (MTTR) and 94% root cause accuracy. The service is now billed per second based on operational task time, with credits available for AWS Support customers. AWS also announced the general availability of Security Agent for on-demand penetration testing.

Key takeaway

For Directors of AI/ML evaluating operational efficiency tools, AWS DevOps Agent offers a compelling solution to reduce incident MTTR and improve root cause accuracy. Its autonomous investigation capabilities and broad integration with existing observability and CI/CD tools can significantly offload SRE teams. You should assess its cost structure against potential savings in operational overhead and consider its applicability to your hybrid cloud environments.

Key insights

AWS DevOps Agent uses generative AI to autonomously investigate incidents and automate operational tasks across diverse environments.

Principles

• AI agents enhance SRE efficiency.
• Autonomous investigation reduces MTTR.
• Extensibility is key for operational data integration.

Method

The agent correlates telemetry, code, and deployment data from various sources (CloudWatch, PagerDuty, GitHub) to triage issues, identify root causes, and recommend preventive actions without human prompting.

In practice

• Integrate with existing observability tools.
• Configure webhooks for incident triggers.
• Develop custom agent skills for specific needs.

Topics

• AWS DevOps Agent
• Generative AI
• Incident Investigation
• Operational Automation
• Amazon Bedrock AgentCore

Best for: CTO, Director of AI/ML, VP of Engineering/Data, MLOps Engineer, DevOps Engineer, Software Engineer

Related on AIssential

• Presentation: DevOps Modernization: AI Agents, Intelligent Observability and Automation — AI agents are transforming DevOps by enabling predictive operations, intelligent rollouts, and machine-speed incident remediation.
• Build an agentic incident triage assistant with Amazon Quick and New Relic — An AI agent can automate incident triage by integrating observability and task management tools into a single conversational workflow.
• Building an Autonomous SRE Incident Response System Using AWS Strands Agents SDK — Multi-agent AI automates SRE incident response from alarm to remediation and reporting.
• AgentWatch: Proactive AWS monitoring with ambient agents — AgentWatch uses ambient AI agents for proactive AWS monitoring, balancing automation with human oversight via specific interaction patterns.
• AWS says AI agents lack business context and security, launches two services to patch the gaps — AWS addresses AI agent production challenges by integrating security automation and business context via new services.
• Introducing Genie ZeroOps: Put your data and AI operations on autopilot — Purpose-built agents integrated with data platforms are essential for autonomous, safe data and AI operations.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by InfoQ.