The ability to engage and retain players is perceived as a major factor in the success of games. However, the end-goal of retention differs between entertainment and serious contexts. For an entertainment game, engagement and retention are linked to monetization; for a serious game, this needs to persist for as long as is required for learning or behavioral objectives to be met. User engagement is strongest when a balance is achieved between difficulty and skill, leading to a state of "flow." Hence, adapting difficulty could lead to increased and sustained engagement. Implementing this requires the identification of variables linked to mechanics, manipulated based upon a player performance model. In some cases, this is possible by adjusting simple properties of objects, though more comprehensive solutions require extending or adapting content applying procedural techniques. This paper proposes a six step plan, validated against two case studies: an existing serious game, with easily manipulated parameters, and a platformer game built from scratch, where additional content is required, showing the process for different mechanics. To explore limitations, the results of two small-scale user evaluations with 45 users in total, are reported, contributing to the understanding of how adaptive difficulty might be implemented and received.