Besides the benefits of flexible processes, practical implementations of process aware information systems have also revealed difficulties encountered by process participants during enactment. Several support and guidance solutions based on process mining have been proposed, but they lack a suitable semantics for human reasoning and decisions making as they mainly rely on low level activities. Applying design science, we created FlexPAISSeer, an intention mining oriented approach, with its component artifacts: 1) IntentMiner which discovers the intentional model of the executable process in an unsupervised manner; 2) In-tentRecommender which generates recommendations as intentions and confidence factors, based on the mined intentional process model and probabilistic calculus. The artifacts were evaluated in a case study with a Netherlands software company, using a Childcare system that allows flexible data-driven process enactment.