This article presents the use of intelligent agents in analyzing the results of electronic tests, based on IMS Question & Test Interoperability (QTI) standard. The results of the analysis show the average assessment of the conducted test, sections of the study material and issues of the test that hinders students. The aim is to support the educational process by creating a personal assistant which will be in service to teachers. The assistant will be developed like a multi-agent system of rational agents or such based on BDI (Beliefs, Desires, Intentions) architecture.