Engineering Robustness into Personal Agents with the AI Workflow Store

ArXi:2605.10907v1 Announce Type: cross The dominant paradigm for AI agents is an "on-the-fly" loop in which agents synthesize plans and execute actions within seconds or minutes in response to user prompts. We argue that this paradigm short-circuits disciplined software engineering (SE) processes -- iterative design, rigorous testing, adversarial evaluation, staged deployment, and -- that have delivered the (relatively) reliable and secure systems we use today.