The article argues that when you find yourself repeating the same prompts with AI agents, it’s smarter to build a “loop” – a system combining intent, context, action, evaluation, memory, and a stop condition – rather than manually steering each step. It shows how to calculate when a loop’s upfront cost pays off over repeated tasks and gives examples ranging from CI checks to goal-based agent scripts.

State AI laws face constitutional limits under the dormant Commerce Clause, but courts lack the data to weigh interstate burdens against local benefits. The article argues policymakers must build evidentiary records—through standardized burden and benefit estimates—and equip judges with analytical tools for effective cost-benefit review.