Abstract: Proposed by Stein (1972) as a method for bounding the approximation error between the distribution of the sum of random variables and the Gaussian Distribution, and extended by Chen (1975) for the Poisson Distribution, the Chen-Stein Method is a powerful technique in Probability Theory that allows to find bounds for the approximation error between the distribution of the sum of random variables, independent or dependent, and its limit distribution. The generality of the method has been established in the past decades, as it has been successfully applied to a great number of distributions, providing better bounds for approximation errors than Fourier Methods, and being most successful in bounding approximation errors for the distribution of sum of dependent random variables. In this talk we will give an overview of the Chen-Stein method and present some research perspectives. We will show that the method may be carried by solving a Poisson equation related to a suitable Makov Process, and then bounding an expectation of the generator of such process applied to this solution.