The concept of interaction is central to multi-agent systems. An interaction occurs when two or more agents come into dynamic relationship through reciprocal actions. A scenario is envisaged in which agents have tasks to perform and are in a position to exchange tasks to improve their performance. This affects the overall performance of the system, but possibly, but not necessarily improves the overall performance of the system. The computing machines, especially the personal computers are intended to be operating as stand alone machines and therefore are endowed with a variety of resources. The demands on these resources are uneven on a machine as well as across the machines. Such diversity offers scope interactions resulting cooperation to meet individual goals as well as for overall system performance. Our model, attempts to illustrate the concept by using two computing machines with their usual resources, and with random initial jobs to be processed. Their performance is dependent not only on absolute total load but also on how much of each machine?s resources are in demand, thus giving scope for the beneficial exchange of jobs. This paper describes the development of a negotiation mechanism for job exchange between machines and measurement of system performance. The concept may be extended to multiple machines that act as agents exchanging resources and tasks.