Technological advances, such as artificial intelligence, would be of great help to improve the agricultural sector, not only in terms of its efficiency, but also to improve environmental and social aspects. One possible application is the automation of decision making –administrative, commercial, logistical, etc.– since it would speed up the decision-making process and improve the results obtained (for example, by considering the common interest in collaborative environments). But, these automated decision makers should only be trusted if they have the ability to explain their decisions, so that they can be properly audited. Logic-based models have an edge over other machine learning techniques in complying with this principle due to their inherent explainability. However, logic based models and their explanations may expose sensitive information, e.g., business secrets. In this work, we propose the use of s(CASP), a reasoner that is capable of providing explanations for their decisions, and to protect the confidentiality of the users we use \(f_{CASP}\) , a forgetting operator that removes sensitive data (from the model and the explanations) without affecting the decision. In this paper, we present as use case, the energy assignment in agricultural cooperatives, where the cooperative is responsible for the generation and distribution of the energy. In this scenario, we consider that the energy assignment must follow human values, such as fairness, and not utility functions. To compute the fairness function we use as a guide the principles of the Common Agricultural Policy.