Usually human evaluation is necessary when the form of fitness function is not known (for example, visual appeal or attractiveness; as in Dawkins, 1986[1]) or the result of optimization should fit a particular user preference (for example, taste of coffee or color set of the user interface).
In addition, human evaluations are slow and expensive as compared to fitness function computation.
There is also evidence that the addition of computational agents can successfully counteract user fatigue.
An example of this approach is an interactive media installation by Karl Sims that allows one to accept preferences from many visitors by using floor sensors to evolve attractive 3D animated forms.
The main application of these techniques include domains where it is hard or impossible to design a computational fitness function, for example, evolving images, music, various artistic designs and forms to fit a user's aesthetic preferences.