{"resourceId":"brenau-fnp-socratic-chatgpt-tutor-pilot-20261106","versions":[{"version":"external-9ec353b069dfe9e2670293523d4dcc28301bc48bcfaa0b495ab8bdaf578a73e3","resource":{"id":"brenau-fnp-socratic-chatgpt-tutor-pilot-20261106","title":"Brenau University (6 Nov): nursing program replaces discussion posts with a Socratic ChatGPT tutor and reports record exam scores, without controls or sample data","organization":"Brenau University","sector":"Higher education graduate nursing instruction","geography":"United States (Georgia)","publishedAt":"Brenau University blog, 6 November 2026","publicationDate":"2026-11-06","eventDate":null,"sourceName":"Brenau University","sourceLabel":"Institutional blog Q&A with provost and nursing director","sourceUrl":"https://www.brenau.edu/blog/ai-tutor-helps-nursing-students-develop-critical-thinking-skills/","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["knowledge-work","operating-model","accessibility-workforce"],"finding":"Brenau says its Family Nurse Practitioner students, in Adult Health and Geriatrics, now work through clinical cases with a customized ChatGPT tutor that asks questions, probes rationale, raises alternative diagnoses and challenges test and prescription choices; conversations replace discussion-board posts and are used to assess critical thinking. The tutor was built and tested in Fall 2025. The director reports that FNP students taking a standardized exam at the end of spring 2026 scored higher than any cohort in the last decade, that a summer cohort scored poorly on a pathophysiology practice exam so the tutor was extended to walk through pathophysiology, and that early results show further quiz improvement. Students reportedly spent more time and effort but felt they learned and remembered more.","sledRelevance":"A concrete example of a Socratic, assignment-embedded tutor in a clinical program with the transcript used as evidence of thinking, and of iterating the tutor from exam data; relevant to programs designing AI to make learning harder to bypass.","evidence":"Institution-authored Q&A. No sample sizes, comparison group, statistics, exam names or timeline detail; outcomes are operator claims and cannot be attributed to the tutor.","architectureImplications":"A customized general-purpose chatbot configured with a Socratic prompt and case content; transcripts are captured as assignment evidence. The article gives no platform, retention or integration details.","governanceImplications":"An AI Task Force within the college chairs the work; the program uses conversation transcripts for assessment, which requires clear rules on what students must submit.","securityPrivacyImplications":"Student conversations with a third-party chatbot become graded artifacts; nursing cases may involve patient-like scenarios, and the article does not discuss data handling.","caveats":"Single program; vendor-like self-report; no control group; cohort differences and curriculum changes are confounds; satisfaction is reported anecdotally.","streamIds":["student-success"],"roles":{"sales":"Sales framing: programs want AI that forces students to think rather than paste answers. Brenau describes a Socratic tutor that replaces discussion posts and uses the conversation as evidence of reasoning, plus a loop that updates the tutor from exam data. That frames a bounded design-and-evaluation engagement for one clinical program. The source is a provost blog with no controls or sample sizes, so do not promise exam gains or time savings; the record cohort result is not attributable to the tutor.","engineering":"Engineering framing: fit is a configured chatbot with Socratic instructions and case content, capturing transcripts for assessment. Questions to resolve include which model and tenancy are used, how transcripts are stored and shared with instructors, identity and enrollment links, and handling of patient-like case details. Validate by comparing a controlled section with and without the tutor on common assessments, and by testing prompt behavior for incorrect clinical guidance before expanding.","delivery":"Delivery framing: faculty own tutor design, testing and updates, so delivery should set a review cycle, case content ownership and a rubric for grading transcripts. Brenau reports students spent more time and effort, so plan workload and support. Governance checkpoints include clinical accuracy review and data handling. Acceptance should be measurable, such as rubric scores and exam comparison against a baseline, because the source offers no outcome statistics."},"roleDetails":{"sales":{"customerProblem":"Graduate programs need AI-era assignments that cannot be completed by pasting a prompt and that still show clinical reasoning.","stakeholders":["Provost","Program director","Clinical faculty","AI task force","Students"],"discoveryQuestions":["How are transcripts graded and stored?","What baseline exam data exist for comparison?","Who updates the tutor when cohort results change?"],"valueHypothesis":"Interpretation: Socratic assignment design may increase visible reasoning evidence; Brenau's source reports effects without controls.","potentialEngagement":"Tutor design and evaluation for one clinical course: rubric, content review, transcript policy and a controlled comparison.","unsupportedClaims":["Tutor caused record exam scores","Time savings","Generalization beyond one program"]},"engineering":{"fit":"Custom-configured commercial chatbot embedded in graded case assignments.","architectureIntegration":"Course enrollment, transcript capture and export to the grading workflow, with case content versioning.","prerequisites":["Approved case library","Transcript storage policy","Accounts or tenancy for students"],"constraints":["Single-program, self-reported results","No platform or retention detail given","Clinical accuracy risk"],"security":"Review data handling for conversations and case content; exclude real patient information.","proofOfValue":["Run controlled sections on common exams","Red-team tutor for wrong clinical advice","Check transcript grading consistency across graders"]},"delivery":{"work":"Maintain case library and tutor prompts, grade transcripts, and run exam-informed updates.","dependencies":["Clinical faculty","IT or AI task force","Assessment office"],"ownership":"Program director with the school AI task force","skillsAdoption":"Faculty need prompt-design and review skills; students need guidance on engaging critically with a Socratic tutor.","governanceCheckpoints":["Clinical accuracy review before each term","Data-handling review","Mid-term student workload check"],"acceptanceCriteria":["Proposed: rubric inter-rater agreement on transcripts","Proposed: exam comparison against a prior or parallel cohort","Proposed: student time-on-task reported"],"risks":["Added student workload","Unreviewed tutor errors in clinical reasoning","Confounded outcomes mistaken for tutor effect"]}},"retrievedAt":"2026-11-11T04:15:58Z","enrichedAt":"2026-11-11T04:19:00Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Faculty must design and update the tutor from performance data; students report added time and effort. Accessibility is not discussed.","procurementImplications":"Uses a commercial chatbot platform with a custom configuration; the article gives no licensing or cost information.","operatingModelImplications":"Faculty own prompt design and iteration; the provost and task force sponsor adoption; exam data feeds tutor changes.","peerReview":"unknown","sourceVerification":{"openedUrl":"https://www.brenau.edu/blog/ai-tutor-helps-nursing-students-develop-critical-thinking-skills/","referenceExcerpt":"students taking a standardized exam in the FNP program scored higher than any cohort in the last decade.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}