From Crafting Text to Crafting Thought: Grounding AI Writing Support to Writing Center Pedagogy

TL;DR

The paper investigates how AI writing tools can support writers without replacing their agency by grounding AI feedback in writing center pedagogy. Through formative interviews with 10 tutors, it derives seven design guidelines and implements Writor, a prototype delivering non-directive, process-oriented feedback with minimal verbatim text. An expert review with 30 instructors, tutors, and AI researchers finds Writor generally aligns with core pedagogy, enhances balance and tone, and is best used to complement human feedback in pre/post-session contexts. The work contributes a principled design framework for AI writing tools, discusses trust-building with AI-skeptical educators, and proposes integration strategies within human writing ecosystems plus avenues for adaptive, granular feedback. These findings have practical implications for developing responsible, pedagogy-grounded AI writing assistants that support learning and writing development rather than substitute human guidance.

Abstract

As AI writing tools evolve from fixing surface errors to creating language with writers, new capabilities raise concerns about negative impacts on student writers, such as replacing their voices and undermining critical thinking skills. To address these challenges, we look at a parallel transition in university writing centers from focusing on fixing errors to preserving student voices. We develop design guidelines informed by writing center literature and interviews with 10 writing tutors. We illustrate these guidelines in a prototype AI tool, Writor. Writor helps writers revise text by setting goals, providing balanced feedback, and engaging in conversations without generating text verbatim. We conducted an expert review with 30 writing instructors, tutors, and AI researchers on Writor to assess the pedagogical soundness, alignment with writing center pedagogy, and integration contexts. We distill our findings into design implications for future AI writing feedback systems, including designing for trust among AI-skeptical educators.

Figures (19)

• Figure 1: Interview insights and design guidelines categorized by writer-centered, process-oriented, and collaborative. Based on insights from formative interviews with writing tutors, we identified seven core design guidelines.
• Figure 2: Illustration of Preparation & Goal Setting Stage of Writor: (A) entering writing task’s purpose and requirements, (B) selecting goals to focus on during revision, (C) enter the essay, and (D) review the input and selected goals. See Fig. \ref{['fig:interface-goal-real']} in the appendix for actual system interfaces.
• Figure 3: Edit Interface of Writor: (a) Expandable button for viewing selected writing goals; (b) Highlight & Get Feedback for user-initiated analysis; (c) Interactive highlighting that connects feedback to specific text; (d) Progress bar for tracking addressed feedback items; (e) Critique and praise cards.
• Figure 4: Study 2 Complete Workflow
• Figure 5: Participant ratings of Writor's alignment with writing center pedagogical principles across three key dimensions: writer-centered, process-oriented, and collaborative. Color indicates their agreement levels, and the number inside each segment indicates the number of participants. Below each statement is the associated design guideline. As a note, G5 (Aligns with Goals) was not presented in the survey because participants were not required to go through the goal-setting stage. We also include supplementary analyses by participants’ writing-instruction backgrounds (Fig. \ref{['fig:wc_role']}) and by their attitudes toward AI (Fig. \ref{['fig:wc_attitude']}) in Appendix \ref{['sec:append_results']}.