During task composition, such as can be found in distributed query processing, workflow systems and AI planning, decisions have to be made by the system and possibly by users with respect to how a given problem should be solved. Although there is often more than one correct way of solving a given problem, these multiple solutions do not necessarily lead to the same result. Some researchers are addressing this problem by providing data provenance information. Others use expert advice encoded in a supporting knowledge-base. However, users do not usually trust complete automation during decision-making for certain domains with natural variation, like biology; they need a way to be able to control and/or intervene with the system´s reasoning to verify parts of the process. This book provides a thorough analysis of the problem and presents a data-centric methodology of measuring decision criticality and describe its potential use. We argue that agent technology is a natural fit for the design of distributed heterogeneous integration systems, particularly in bioinformatics, and we propose a multi-agent system design and architecture as the basis of our framework.