Maintaining products at scale means continually investigating bugs, responding
to regressions, and finding problems before users report them.
This talk explores how AI agents can support a continuous maintenance loop, from discovering and triaging issues to proposing fixes and verifying outcomes. We’ll examine the engineering challenges behind these systems: providing the right product context, coordinating specialized agents, following work through to completion, and measuring quality.
We’ll also discuss how to expand autonomy as reliability improves, while keeping engineers in control of consequential decisions. Attendees will leave with practical design principles for bringing agentic maintenance into their own engineering workflows.
