A super-agent is an aggregation of lesser agents, just as a person is an aggregation of cells, a corporation is an aggregation of people, flock is an aggregation of birds, and a complex program is an aggregation of routines. The aggregation schemes (organizations) synthetic super-agents often use mechanisms borrowed from other systems. For instance, the hierarchical structures of modern corporations can be traced back to those of ancient tribes, the alternating cycles of creation and destruction in genetic algorithms have been adapted from the theory of evolution, and the arrangements of artificial neural nets have been borrowed from models of the human brain. Where might the designer of future super-agents look for mechanisms to borrow and adapt? How should such mechanisms be combined? More generally, how should the synthetic super-agents of the future be designed?