The test is a significant aspect of software development and plays a considerable role in detecting errors in the implementation phase. As the software becomes more pervasive and more often employed to achieve critical tasks, it will be increasingly required to be of high quality. Unless, we can find efficient ways to perform effective testing, the percentage of development cost devoted to the test process will increase significantly. In this study, we propose a multiagent system using agents to provide assistance during the whole testing process. This system has several characteristics. Firstly, it minimizes the interference of the tester by automating the process of test. Secondly, by intellectually selecting redundant free and consistent and effective test cases, the testing time is reduced while the fault detection ability increases. Thirdly, architecture suggested is open and extensible. It supports dynamic addition, suppression of the agents and the services. Lastly, the agents can be located in only one computer or a network.