Objective

Sense Education represents the first Artificial Intelligence solution for finding patterns and providing personalized feedback in student submissions using unsupervised learning and natural language processing.

Improve feedback delivery through better UX for instructors and students
Incorporate gamification and motivation principles into the student experience
Elevate the MVP to support pilots at scale (starting with Computer Science)

RESULTS

I delivered an enhanced MVP that improved the experience for both instructors and students.

For instructors, the redesigned platform introduced a streamlined workflow for reviewing student submissions and providing feedback. An AI-powered dashboard surfaced patterns, common errors, and grading progress—reducing manual effort and improving efficiency.

For students, the platform offered step-by-step performance breakdowns, timely feedback, and motivational prompts throughout each assignment. A personalized dashboard allowed students to track progress and access helpful resources across the semester.

How it Works

USERS & STRATEGY

The platform serves:
Instructors: Professors and TAs who assign and grade open-ended submissions
Students: Learners who receive dynamic, AI-generated feedback

We focused first on Computer Science due to:
• High volume of open-ended assignments
• Need for scalable feedback
• Clear application of pattern detection and code clustering
• Strong potential for adaptive learning and motivation tools

THE STARTING POINT

The original platform was built by engineers and lacked a user-centered design. It supported only instructor workflows and prioritized functionality over clarity or usability.

Research: Student Feedback

After meeting with stakeholders and auditing the platform, I focused my research on how to deliver feedback that is timely, motivating, and effective—particularly for students working through open-ended assignments.

I explored current trends in EdTech, then looked beyond education to apps like Starbucks, which use gamification and rewards to sustain engagement. These models offered valuable insights into reinforcing behavior, celebrating progress, and encouraging re-engagement.

Key insights

Feedback should be immediate and actionable

The tone should be positive and motivating, even when scores are low
Progress tracking should give students a clear sense of momentum
Elements of gamification—like affirmations and nudges—can enhance persistence

Creating an Assignment

This user flow illustrates the instructor’s experience in creating assignments and integrating them with AI for the purpose of analyzing student submissions for common patterns.

AI groups similar submissions using unsupervised learning
Natural Language Processing (NLP) generates cohort-level feedback that instructors can personalize
Dashboards show grading status, trends, and common errors

User Testing

I conducted rapid, guerrilla-style user testing within a tight timeline and budget. For this study, I enlisted students from Georgia Tech, where Sense was piloting the platform. In moderated sessions, students provided critical feedback on the initial design concept, which directly informed a series of iterative refinements.

“I would like to see my status regarding the completion of the course.”

“I do not understand the significance of the colored bar next to the code.”

“I like the positive tone - I would have been disappointed with an 80, but was not discouraged.”

DESIGN APPROACH:

The final MVP prototype was built after 3 months of definition, discovery, testing and iterations. These screens represent the experience for both the Instructor and the Student application.

Instructor EXPERIENCE: assignments

The redesigned instructor experience streamlines the process of creating assignments, analyzing submissions, and delivering feedback.

AI employs rules and queries to detect patterns, categorizing submissions into logical groups based on similarities in problem-solving approaches.
Each criterion is assigned a prioritization level (low, medium, high), which guides the AI in data weighting when running the model.
The instructor provides feedback at the group level, providing one comprehensive set of comments per group, enhancing and streamlining the evaluation process.

Instructor: Dashboard

The dashboard presents a comprehensive view of all student assignments,

Offers educators a strategic snapshot that includes the volume of submissions over time, coupled with insights into overall student performance and success rates.
Detailed assignment analytics feature the quantity of patterns and groups specified per assignment, empowering educators with the capability to refine feedback directly and export data for further evaluation or reporting purposes.