This paper reports MALESAbrain an intelligent online tool for problem-based learning (PBL) in IT education. The learning model of MALESAbrain is built on the notions of threshold and knowledge-weight from the discipline of machine learning. MALESAbrain encourages learners to judge or critically evaluate the solutions posted by others before exploring further knowledge-content. The intelligent MALESAbrain then sums up the judgment scores as its knowledge-weight to pass the thresholds set up for ranking/arranging the learning issues. This constraint design for judgment, therefore, becomes a mechanism for critical thinking in a problem-based learning activity. The intelligent system transforms the forum and chat room into rich learning environments. MALESAbrain advances online discussion services more efficient and effective in PBL.