In introductory programming courses, autograders typically evaluate student programs by running test cases without inspecting the source code. However, educational grading often requires manual code inspection for two key reasons: (1) to award partial marks for code that may fail test cases but is partially correct, and (2) to assign marks based on code quality or specific criteria set by the instructor, such as requiring a particular algorithm like bubble sort. Rubric-based subjective grading is beneficial for these reasons, but manual grading for large course enrollments is a time-consuming task. This demo introduces TA Buddy, an AI assistant designed to streamline grading in introductory programming courses like CS101. Powered by the LLM CodeLlama and integrated with IIT Bombay’s BodhiTree-Evalpro platform, TA Buddy suggests grades and provides reasoning for the suggested grades. These features help instructors and teaching assistants grade student submissions more efficiently. Its key benefits include speeding up the grading process with AI-generated suggestions and providing detailed feedback with clear justifications for assigned grades, making it highly relevant for large courses where manual grading is time-consuming.