Imagine a world where grading essays is no longer a time-consuming chore for teachers. Researchers are exploring how Large Language Models (LLMs), the technology behind AI chatbots, can automate and explain essay scoring. This innovative approach, exemplified by a system called AERA Chat, aims to provide fast, consistent, and transparent grading. AERA Chat allows educators to input questions, student answers, and grading rubrics, then uses LLMs to generate scores along with detailed explanations of the reasoning behind each mark. This not only speeds up the grading process but also offers valuable insights into how the AI arrives at its decisions, addressing concerns about the 'black box' nature of traditional automated scoring systems. What's truly unique about AERA Chat is its interactive interface, which lets educators delve deeper into the AI's rationale, even allowing them to correct the AI or provide their own annotations. This feedback loop is crucial for refining the system and ensuring it aligns with educators' expertise. While this technology offers tremendous potential for streamlining assessment, researchers are also mindful of the challenges. Ensuring the fairness and accuracy of AI-generated scores, especially across diverse student populations and writing styles, is paramount. The development of AERA Chat represents an exciting step towards a future where AI assists educators in providing more efficient and insightful feedback to students, ultimately enhancing the learning experience.