Revision is a crucial component of the writing process, yet few formative assessments focus on young students’ revision processes. This study explored an AI-assisted formative assessment that identifies revision patterns across drafts of students’ text-based argument writing. We examined the performance of GPT-4.1 in predicting revision patterns using few-shot prompting and few-shot Chain-of-Thought prompting. The results show that GPT-4.1 has strong potential for evaluating the revision process for formative purposes, with excellent intra-rater reliability across multiple runs. Chain-of-Thought prompting that incorporates intermediate evaluation steps improved the accuracy of predicting explanation-focused revision patterns.