Agentic DevOps at AWS

2026-07-16 · Source: Software Engineering Daily · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cloud Computing & IT Infrastructure · Depth: Intermediate, extended

Summary

AWS's Agentic DevOps initiative applies AI agents to address persistent pain points in software delivery and operations, aiming to match modern development velocity with an equally capable operational layer. Neha Kazwami, who leads Agentic DevOps at AWS, discusses how their DevOps Agent works from alarm to root cause, achieving 85% to 95% accuracy internally and 94% root cause accuracy in preview. The agent integrates with diverse tools like GitLab, Datadog, Splunk, and ServiceNow, reflecting AWS's philosophy of meeting customers where they are. Amazon internally "dogfoods" these tools, with developers owning end-to-end operations and using agents to automate incident response and large-scale changes like Java version upgrades, saving millions of dollars.

Key takeaway

For mid-career DevOps and SRE engineers concerned about evolving roles, embrace agentic tools to automate routine tasks and focus on complex problem-solving. Start experimenting with these tools to understand their capabilities and identify areas where your expertise can address more intricate challenges, moving up the stack to higher-value work. This shift will redefine your role from reactive incident response to proactive system optimization and advanced problem resolution.

Key insights

AI agents apply reasoning and tool-calling to automate DevOps pain points, enhancing operational velocity and safety.

Principles

• Prioritize customer needs over building new services.
• End-to-end ownership improves service sustainability.
• Inject determinism for safety and security.

Method

The AWS DevOps Agent models system topology, correlates data from various sources (e.g., CloudWatch, Datadog, Splunk), and provides root cause analysis and mitigation steps for incidents.

In practice

• Automate incident response and root cause analysis.
• Customize agents with bespoke runbooks for higher accuracy.
• Integrate agents with existing ticketing and logging systems.

Topics

• Agentic AI
• DevOps Automation
• Incident Response
• Site Reliability Engineering
• Cloud Operations
• LLM Evaluation

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

Related on AIssential

• Scaling cloud maturity with AI and AWS DevOps Agent: PwC — The AWS DevOps Agent uses agentic AI to unify telemetry, identify root causes, and automate incident response across hybrid cloud environments.
• Redefining the future of software engineering — Agentic AI is poised to automate end-to-end software development and product lifecycles, driving significant speed and efficiency gains.
• From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud — Automating performance investigation and verified fixes with AI agents can proactively address the "leaky bucket problem."
• AWS Announces General Availability of DevOps Agent for Automated Incident Investigation — AWS DevOps Agent uses generative AI to autonomously investigate incidents and automate operational tasks across diverse environments.
• 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.
• Agentic AI–Powered DataOps for Cloud-Native Digital Transformation — Agentic AI transforms DataOps into a proactive, self-optimizing ecosystem for cloud-native data management.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Software Engineering Daily.