Study Finds That Claire AI® Cuts Item-Writing Time for Nurse Educators by 67%
Newly published research found that Claire AI® reduced the amount of time nurse educators spent writing test items by 67% and maintained comparable item quality, providing objective support for its use in academic nursing programs.
The study, titled Effectiveness of AI-Assisted Item Writing in Nursing Education: A Mixed-Methods Evaluation, was published in the peer-reviewed Journal of Professional Nursing in September 2026.
In their research, lead author Hanwook Yoo, EdD, Psychometric Manager at Ascend Learning, and five coauthors sought to determine whether targeted artificial intelligence assistance with Claire AI could increase the efficiency of item development without compromising quality. ATI is an Ascend Learning brand.
“Traditional item writing is time-consuming and often results in flawed items due to lack of faculty training,” the authors wrote. “By evaluating an AI-powered item writing tool, ATI's Claire AI, this research illustrated how technology could reduce nurse educators' workload in item writing while ensuring that student assessments were well-aligned with educational standards.”
Claire AI is the AI assistant purpose built by ATI for nursing education. In ATI’s Custom Assessment Builder, Claire AI helps faculty generate and fine-tune NCLEX-style items and complete exams.
Phase 1: Measuring Efficiency and Item Quality
For this study, researchers used a three-phase mixed-methods design that combined an observed item-writing comparison, faculty interviews and a national survey.
In the first phase, nine nurse educators completed item-writing training and created questions both manually and with Claire AI assistance. Together, they produced 335 items during two 90-minute writing sessions. Researchers measured the time required to create each item and the number of items produced.
Also in this phase, two experienced nursing education specialists independently evaluated the items using five criteria: clarity, relevance, cognitive level, defensibility, and distractor plausibility.
The results documented a significant difference in the time required to develop items. When writing question manually, faculty took an average of 10.69 minutes per item. When they used Claire AI, the average dropped to 3.49 minutes — a 67% reduction.
The volume of questions produced increased markedly. The educators generated approximately three times as many items during AI-assisted writing sessions than during manual sessions.
The study also identified how AI assistance changed the time spent on both steps in item generation, drafting and revising:
➡️ Manual: average 9.13 minutes drafting, 1.56 minutes revising
➡️ AI assisted: average 1.46 minutes drafting, 2.03 minutes revising.
Rather than eliminating faculty work, the authors explained, Claire AI shifted more of that work from creating an initial draft to evaluating and refining one.
AI assistance also allowed participants to nearly triple the number of items generated during the item-writing sessions: an average of 28.2 with AI compared with 9.0 created manually.
Of note, the increase in efficiency was not associated with a meaningful decline in item quality. Overall quality ratings were comparable: 19.8 out of a possible 25 for AI-assisted items and 19.4 for manually written items.
Phase 2: Moving Beyond the 'Blank Page'
In the second phase, cognitive interviews conducted provided additional insight into the faculty experience.
Participants described generating the initial idea for a question as one of the more time-consuming parts of manual item writing. Having an AI-generated starting point helped reduce that “blank page” burden by giving faculty a stem or question concept they could evaluate and improve rather than requiring them to start from scratch.
Faculty described Claire AI as easy to use and noted a specific potential value for educators who are new to item writing. Developing effective assessment questions requires specialized knowledge that many nursing faculty must acquire after moving from clinical practice into education. Participants suggested that an AI-assisted tool could provide new faculty with a starting point as they develop those skills.
Faculty Expertise Remains Essential
In addition to efficacy and quality, the study findings also highlight an important limitation of AI-assisted item writing: the need for a human in the loop. Faculty expertise and review remain essential.
Participants and expert reviewers identified distractor plausibility as a particular area requiring faculty judgment. Some AI-generated distractors were too obvious or implausible, and participants reported spending much of their revision time strengthening answer options.
During this study, the two participants whose AI-assisted items received slightly lower average quality scores made little or no edits to those items. This finding reinforces the role of AI as a support tool rather than a replacement for educator expertise.
Faculty remain responsible for reviewing AI-generated items for content accuracy, appropriateness, cognitive complexity, defensibility and alignment with course and program expectations.
Phase 3: Survey Findings Document Item-Writing Burden
The third phase of the research evaluated responses from 250 nurse educators in a nationwide survey about exam development and time management.
The results reflect how time-intensive item writing can be. Nearly 75% of educators reported that manually writing a single exam question typically takes 15 minutes to 1 hour.
When asked how long the same task would take using an electronic exam-preparation resource such as an AI item-generation tool, 56% said less than 15 minutes. In addition, 77% identified automated test-generation tools as a resource that could help reduce the time they spend writing exams.
These survey findings provide broader context for faculty workload and perceptions of AI-assisted resources. Survey responses were collected separately from the item-writing comparison of Claire AI conducted in the first phase of the study.
Growing Evidence for Appropriate Use of AI in Nursing Education
This new research adds empirical evidence to a rapidly evolving discussion about how nursing faculty can use AI responsibly and effectively to support education and improve workflows.
For nurse educators, Claire AI can substantially reduce the time required to draft a workable item. At that point in the process, faculty expertise remains central to ensuring the final question meets the standards required for nursing education.
“The message from this research is not that AI replaces faculty expertise. It reinforces the opposite,” said coauthor Beth Phillips, PhD, RN, CNE, a former nurse educator and program director who is now Strategic Nursing Advisor for ATI. “Tools like Claire AI can help educators create assessment content more efficiently, but nurse educators remain essential to ensuring quality, clinical relevance, and sound judgment. The real opportunity is using AI to elevate the work of faculty, not replace it.”
Study Citation
Yoo H, Lin Y, Attenweiler R, Hodge KJ, Miller JE, Phillips BC. Effectiveness of AI-Assisted Item Writing in Nursing Education: A Mixed-Methods Evaluation. Journal of Professional Nursing. 2026;67:284–293. https://doi.org/10.1016/j.profnurs.2026.09.001
For Further Reading on AI-Assisted Item Writing
Meeting the Challenges of Exam Development With Artificial Intelligence
Meeting the Challenges of Item Writing With Assistance From Artificial Intelligence