Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants

arXiv:2603.03565v1 Announce Type: new Abstract: Conversational shopping assistants CSAs represent a compelling application of agentic AI, but moving from prototype to production reveals two underexplored challenges: how to evaluate multiturn interactions and how to optimize tightly coupled multiagent systems. Grocery shopping further amplifies these difficulties, as user requests are often underspecified, highly preferencesensitive, and constrained by factors such as budget and inventory.