This study investigates the effects of using an online Automated Essay Assessing (AEA) system on EFL graduate students' writing. Eighty four EFL graduate students divided into the treatment group and the control group participated in this study. The treatment group was asked to use an AEA system to assist their essay writing. Both groups were pretested before the treatment. After the sixteen-week treatment period, the writing posttest was given to both groups to measure their progress in their writing. The results indicate that, although both groups have no significant difference in the pretest, the difference between their mean scores on the posttest is statistically significant. The mean score of the treatment group is higher than that of the control group, and students' use frequency of the AEA system is closely related to their writing improvement. Therefore, it is concluded that, students' using the AEA system contributes significantly to their writing improvement. Thus a linear regression is modeled to predict the weight of the AEA system use frequency to proficiency improvement in writing. Finally, students' perceptions based on their learning journals and interviews show the changes in the process of writing.