Fuzzy logic (FL), Neural Networks (NN) and Genetic Algorithms (GA) are three popular artificial intelligent techniques that are widely used in many applications. Due to their distinct properties and advantages, they are currently being investigated and integrated to form new models or strategies in the areas of system control. One of these areas of system control is water-level-control, which is applied in this research, where a storage tank as a buffer water supply and it is replenished from a mains water pipeline. The tank water level is controlled by an automatic control valve. In this work, FL, NN, and GA were combined to design a Neuro-Fuzzy Controller (NFC). It is based on multi-layer neuro-fuzzy network that is built utilizing Genetic Algorithms (GA). Moreover, NFC is tuned using GA. Then the ineffective rules are removed from the rule-base of the controller. GA is employed to take advantage of search facilities offered by this approach. A real code representation is used to encode the GA chromosome. Two selection methods are" used, namely, Roulette wheel and Tournament selection methods. The steps of building, tuning, and the removal of the ineffective rules are accomplished in an off-line phase. In on-line phase, the resulting NFC is operated and it is noticed that the response of the system is not robust enough. So, to avoid any shortage that may happen in the system performance, an adaptive fuzzy controller is added to the NFC. The research is implemented on PC Pentium II, using C++ programming language.