How can we trust an autonomic system to make the best decision?

Autonomic Computing has gained widespread attention over the last few years for its vision of developing applications with autonomie or self-managing behaviors [1]. New approaches to the design and implementation of autonomie systems have emerged, including the use of goal policies[2], utility functions [2], intelligent monitoring, data mining, reinforcement learning, and planning. Unfortunately, these new approaches do nothing to reduce administrators' skepticism towards automation - how is an administrator to believe that an autonomie system will help his systems perform better? In this report, we describe an approach by which an autonomie system can win the trust of its users, and can continuously adjust itself to make better decisions based on the users' preferences.