Currently submitted to: JMIR Formative Research
Date Submitted: Jul 7, 2026
Open Peer Review Period: Jul 7, 2026 - Sep 1, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
A Socratic AI Writing Tutor That Withholds Draft Text Until the Author Reasons: An Automatic Engagement Gate and Proof-of-Concept Demonstration in Oncology
ABSTRACT
Background:
Large language models (LLMs) can draft manuscript sections on demand. General-purpose conversational tools produce text whenever asked, which can yield manuscripts the nominal author did not reason through, raising educational and academic-integrity concerns and doing little to train the author.
Objective:
We describe and demonstrate a Socratic AI writing tutor whose defining feature is an automatic engagement gate: the tool refuses to produce any draft text until a secondary model judges that the author has substantively engaged with at least three guiding questions.
Methods:
The web application guides the users through eight sequential manuscript modules. Before each turn, a secondary LLM classifies the author's latest reply as substantive or not; draft generation is unlocked only after three substantive replies, and even then, a draft is merely offered for the author to accept and edit, never inserted automatically. The guidance is aligned with the relevant reporting standards for the chosen study design. We illustrate the tool with a fictional retrospective case series (atezolizumab plus bevacizumab in hepatocellular carcinoma) by constructing two manuscript sections. Because this is a demonstration of the intended behavior, both the trainee and tutor turn in the illustrative sessions were generated by a large language model (Claude Opus 4.8); no real users were involved
Results:
In the illustrative sessions, with the gate active, the tutor declined write-for-me requests, converted vague claims into exact figures, corrected two technical errors (censoring and misplaced interpretation), and assembled drafts only from the author's own statements once the threshold was met.
Conclusions:
An automatic engagement gate is a feasible mechanism for keeping an LLM in a tutoring role rather than a ghostwriting role, distinguishing this tool from general-purpose chatbots. Clinical Trial: Not Applicable
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.