“To achieve high productivity gains in software engineering, we need to automate the more complex activities that require a deep understanding of how to go across different tools, how to go across operational boundaries, and use a lot of tribal knowledge so a human doesn’t have to be at the wheel.”
Some of the most challenging problems in software engineering—understanding complex production systems, debugging under pressure, reasoning across massive codebases—are also the most promising applications for agentic AI.
In this conversation, Mayank Agarwal and Rushin Shah (Resolve AI) dive into the current capabilities, fundamental limitations, and open research questions that determine how agentic AI becomes an indispensable tool for software engineering.
They also discuss codegen tools and production problems, including why vibe coding doesn’t go far enough, and how instead, their customers are “vibe debugging” using Resolve. And finally, they give their perspective on team building in agentic AI.
Watch the Panel Discussion
Corinne Riley
Corinne works with early-stage founders who are creating data and AI products at the infrastructure and application layers.
visually hidden
