iGrading is planned as part of the HCT Smart Faculty Assistant platform.
The module will use AI Agent systems and machine-learning techniques to help faculty review
exam submissions, compare answers against rubrics, generate feedback, and support consistent grading.
The goal is not to replace faculty judgment. It is designed to support grading decisions,
reduce repetitive marking effort, and provide transparent recommendations that faculty can review,
approve, or adjust. Because letting an algorithm silently decide grades would be the kind of plot twist
nobody asked for.
Rubric-Based Grading
Evaluate answers using predefined marking criteria, score ranges,
learning outcomes, and assessment standards.
AI Feedback Generation
Generate clear feedback for students based on strengths, missing points,
errors, and improvement areas.
Faculty Review Workflow
Allow faculty to review AI suggestions before finalizing marks,
comments, and grading decisions.
Machine Learning Insights
Support analysis of common mistakes, grade patterns, question difficulty,
and assessment performance.
Final grades should always be reviewed and approved by authorized faculty.
iGrading is intended to assist the assessment process, not replace academic responsibility.