The aim of this paper is to show and illustrate, in a simple language, how neural controllers can easily be designed and implemented in real-time to control a system. We first design and simulate an adaptive neural controller to control a Permanent Magnet DC (PMDC) Motor. The controller is divided into two sections — speed error minimizing and current error minimizing and the two neural controllers (speed and current) are modeled in Simulink. Brandt-Lin adaptation algorithm is used to minimize the error signal. The system is then implemented in real-time with a real motor using dSPACE and the control desk software. Finally, the simulation results and the real-time results are compared and discussed.