To stay competitive, software development companies need to constantly evolve their software development practices. Companies that succeed in shortening customer feedback loops, minimizing the time between customer proof points and learn from customer usage data will be able to accelerate innovation and improve the accuracy of their development investments. While contemporary research reports on a number of well-established techniques for actively involving customers before and during development, there is less evidence on how to successfully use post-deployment customer data as input to the development process. As a result, companies invest significantly in development efforts without having an accurate way of continuously validating whether the functionality they develop is of direct value to customers once the product is taken into use. In this paper, we explore techniques for involving customers and for collecting customer data in pre-development, during development and in the post-deployment phase of software development. We do so by studying three software development companies involved in large-scale development of embedded software. We present an inventory of the techniques they use for collecting customer feedback and we outline the key opportunities for more effective development and evolution based on post-deployment data collection.