This systematic review examines 22 studies (2024-2025) on the use of generative AI, primarily ChatGPT, for providing feedback in English writing instruction for language learners. It identifies the types of feedback AI offers, its effectiveness relative to teacher and peer feedback, and perceptions from students and teachers. Findings show AI excels in addressing surface-level issues (grammar, vocabulary, structure) and is valued for speed and comprehensiveness. However, both students and teachers emphasize the continued importance of human feedback for deeper, contextual revisions. While educators recognize AI's potential to ease workloads and improve feedback timeliness, concerns about reliability and depth persist. The review recommends integrating AI feedback with teacher oversight, training in prompt literacy and feedback evaluation, and calls for further research on long-term impacts, scaffolding strategies, and ethical considerations.