The majority of decisions in the building design process are taken in the early design stage. This delicate phase presents the greatest opportunity to obtain high performance buildings, but pertinent performance information is needed for designers to be able to deal with multidisciplinary and contrasting objectives. In the present work, an integrative approach for the early stages of building design is proposed to obtain detailed information on energy efficient envelope configurations. By means of genetic algorithms, a multi-objective search was performed with the aim of minimising the energy need for heating, cooling and lighting of a case study. The investigation was carried out for an open space office building by varying number, position, shape and type of windows and the thickness of the masonry walls. The search was performed through an implementation of the NSGA-II algorithm, which was made capable of exchanging information with the EnergyPlus building energy simulation tool. The analyses were conducted both in absence and in presence of an urban context in the climates of Palermo, Torino, Frankfurt and Oslo. In addition, a preliminary analysis on the Pareto front solutions was performed to investigate the statistical variation of the values assumed by the input variables in all the non-dominated solutions. For the analysed case study, results highlighted a small overall Window-to-Wall Ratio (WWR) of the building in all locations. Pareto front solutions were characterised by low WWR values especially in east, west and north exposed facades. The area of the south facing windows was higher compared to the other orientations and characterised by a higher variability.