UCSD's mentorAI Collaboration

UC San Diego is teaming up with ibl.ai to support learning outcomes in student writing. Guiding the effort is Dr. Kristina Markman, Associate Director of UCSD’s Humanities Program, whose team will use mentorAI to enhance the quality of instruction and evaluation in high-enrollment, writing-intensive general education courses. Unlike most educational AI tools that focus on aiding students during the drafting process, mentorAI supports instructors and teaching assistants in delivering curriculum-aligned, formative feedback—now with the ability to analyze student writing in the same manner a TA or instructor would. The AI Mentor draws exclusively from a pre-approved comment bank, selecting two of the most relevant comments for each section of a student’s work (e.g., “A topic sentence should present an arguable claim, not just summarize an observation. Focus on stating what the paragraph will prove about the text.”). For each comment provided, the AI Mentor offers a short justification, enabling instructors to select the most appropriate feedback for each student. This approach reduces cognitive load, ensures grading consistency across large multi-section courses, and promotes deeper student engagement with analytical writing—while keeping final judgment in human hands.

---

Why This Matters

The Humanities Program, which serves approximately 1,500 students each quarter, is the cornerstone of UCSD’s liberal arts and writing requirement. The program offers students an interdisciplinary introduction to the history of ideas while honing their analytical writing skills through an evidence-based, text-centered approach. In large, writing-intensive courses like this, students and instructors face unique challenges: ensuring consistency in grading, maintaining high-quality feedback, and preserving space for individual learning. mentorAI addresses these challenges by supporting instructional staff in delivering clear, curriculum-aligned feedback while preserving the human dimension of writing instruction. Dr. Markman’s team and ibl.ai are working to give instructors a common framework that:

• Aligns assessment practices with curricular outcomes.

• Democratizes feedback so students encounter consistent expectations, regardless of which instructor or section they’re assigned.

• Shifts faculty focus from mechanical scoring to thoughtful engagement with student writing and ideas.

• Personalizes the student experience by freeing faculty to create more opportunities for one-on-one tutoring and deeper engagement.

Empowering Faculty First

This project is firmly instructor-centric. mentorAI launches in a private faculty workspace inside Canvas, where instructors and TAs can:

• Upload prompts, rubrics, and exemplar papers to their AI Mentor.

• Have the mentor analyze student writing, select two top comments from the pre-approved comment bank, and provide justifications for each.

• Audit every suggestion before releasing it to students.

This workflow ensures that instructors maintain complete control over the feedback process while gaining time to focus on deeper engagement with students.

Canvas-Embedded, Friction-Free

Because mentorAI integrates natively with Canvas via standards-based links, no extra logins or browser tabs are required. This initiative will allow instructors to simply toggle the tool on for a given assignment, and their AI assistant will appear alongside SpeedGrader. The familiar workflow encourages adoption while keeping all data within UCSD’s existing learning environment.

Security & Institutional Control

All mentor-student interactions are logged for transparency, and UCSD maintains full ownership of both data and model configurations in its private cloud tenant—an approach that aligns with FERPA and minimizes vendor lock-in.

---

Looking Ahead

By prioritizing faculty needs—consistency, efficiency, and pedagogical alignment—UC San Diego is setting a new standard for AI-enhanced writing instruction. The collaboration promises more equitable grading for students and more meaningful time for instructors to teach, mentor, and innovate. The addition of the pre-approved comment bank workflow and justification process further ensures that AI feedback enhances, rather than replaces, the human expertise of UCSD’s instructional staff. Other universities wrestling with large writing programs will be watching closely as Dr. Kristina Markman and ibl.ai demonstrate how generative AI can elevate both teaching quality and student success.