Current approaches to modelling plans and processes in AI are limited by current understanding of “goals” and “intentions”. We discuss this question in a medical context, viewing goals as clinical objectives and plans and processes as collections of tasks to achieve those objectives. The specific context for this discussion is the CREDO project, which aims to develop a comprehensive approach to supporting complex treatment plans and care pathways and provides an opportunity to carry out an extensive investigation of the key problem of formalising goals in medical informatics and AI generally. A review of 222 clinical services required in the management of breast cancer has yielded a systematic classification of tasks involved in breast cancer care and a similar classification of the clinical goals associated with these tasks. A six-component model of goal structure is proposed based on these ontological analyses. Although the model has been derived from a corpus of examples from medicine many of the issues encountered, and the solution proposed, appear to be relevant to other domains.