Site Reliability Engineering (SRE) is undergoing a major shift from manual operations and rule-based automation to intelligent, AI-driven workflows. AI DevOps agents are emerging as powerful assistants that can understand system behavior, analyze large volumes of telemetry data, and actively support engineers in maintaining reliability at scale. In this session, we explore how AI agents are transforming incident detection and root cause analysis to automated remediation and system optimization. Leveraging advances in large language models and integrations across observability and deployment systems, these agents can interpret logs, correlate metrics, and recommend actionable solutions in real time.
Keerthi Sreenivas is a Agentic AI Specialist Solutions Architect at AWS, with over 4 years of experience spanning AI infrastructure, developer experience, and large-scale systems. Previously an Infrastructure Engineer at Barclays, she brings a strong systems-first perspective to modern AI. Keerthi runs @qriositybykeerthi, an edu-tech Instagram platform with over 20k followers, where she simplifies AI for a broad audience. She is an AWS re:Invent 2025 speaker, the author of three AWS blogs, and holds 8 certifications across AWS and NVIDIA.
