Revolutionizing Engineering Support with Agentic AI

Agentic AI systems have achieved wide adoption in software development, assisting engineers with code generation, diagnostics, and efficiency. However, the evolution of AI-powered agents for support engineers and IT operations remains nascent. This paper surveys the landscape of agentic AI in both software development and operational support, examines current capabilities such as observability, root cause analysis, and explores the potential for automated remediation, knowledge-based case resolution, and SME-guided learning. We propose a taxonomy of support-centric AI agent tasks and discuss research and engineering challenges for autonomous, end-to-end product support by AI.
Who is this presentation for?

Prerequisite knowledge:

What you'll learn?

This is Sri Krishna Ravulapalli (also known as Krishna), and I bring over 18 years of experience in software product development since 2007. I hold a Master of Technology in Computer Applications from the Indian Institute of Technology Delhi (IIT Delhi), where my research focused on the Semantic Web. My Master's thesis, published at IICAI-07, explored transforming unstructured text into semantic data to enhance search capabilities. I have since been actively engaged in advancing semantic web concepts. Currently, I am employed at Broadcom as an R&D Software Engineer 4, where I focus on modernizing mainframe applications using AI techniques. My expertise encompasses AI Operations (AIOps), IT Service Management, Data & Analytics, and Enterprise Resource Planning (ERP). Additionally, I am a certified Google Cloud Professional Architect and Data Engineer with extensive experience building retrieval-augmented generation (RAG) interactive applications and data pipelines on the Google Cloud Platform (GCP). My work centers on enhancing software product maintenance and support through advancements in Agentic AI.