By: Stephanie J. Counts, PharmD, MEd
Designing or revising a course rarely begins with a blank page. More often, faculty must reconcile years of syllabi, accreditation standards, assessment tools, and accumulated notes while maintaining alignment among objectives, instruction, and assessment. The challenge is not generating new content, but deciding what to keep, what to change, and what to cut, and being able to explain why. Most AI discussions in health professions education focus on content generation rather than course design.1,3 In contrast, UNESCO describes GenAI as a potential curriculum or course co-designer, but only with clear scope, verification, and active bias management.2
Pharmacy curricula are especially prone to this challenge. With ACPE standards, competency frameworks, IPPEs, and APPEs all exerting simultaneous pressure on course design, it is easy for individual course components to drift out of sync over time, not through carelessness, but through the sheer volume of competing demands.
Unlike general-purpose chat tools that draw broadly from web-based knowledge, NotebookLM allows faculty to anchor analysis in a defined set of materials they select. Its value during course design is not drafting content, but helping instructors see patterns, inconsistencies, and connections across their own materials.
This approach aligns closely with backward design, in which faculty identify desired outcomes and assessments before determining instructional activities.4 NotebookLM can then serve as a tool to check consistency across these elements and maintain coherence throughout the design process.
The Design Challenge Faculty Actually Experience
The difficulty lies not in access to information but in maintaining coherence as a course evolves. As materials accumulate, it becomes harder to track how key elements, learning objectives, instructional activities, assessments, and prior decisions fit together. Drift and gaps can occur when objectives, instruction, and assessment change over time without a clear record of what was decided and why. General-purpose AI chat tools can draft or brainstorm, but sustained analysis across a defined set of materials requires deliberate context management.
What NotebookLM Actually Does?
NotebookLM differs from open-ended chat tools by grounding its analysis in materials the faculty provides. Users can upload course materials, notes, or references and generate summaries explicitly grounded in those sources. It can surface how frequently learning outcomes appear, summarize assessment criteria across documents, or help articulate implicit design logic. Used this way, the tool surfaces patterns, but faculty interpret the findings, make revisions, and re-query for coherence. It supports clearer decision-making rather than substituting for professional judgment. This alignment work supports backward design by helping faculty confirm that assessments measure stated outcomes and that instructional activities prepare students accordingly.
Practical Ways Faculty Might Use It
In practice, NotebookLM can support course design without adding new steps or documentation requirements. Consider a faculty member teaching across Course 1 and Course 2 who wants to ensure that clinical reasoning skills introduced early are intentionally extended rather than unintentionally repeated or abandoned. By uploading existing materials from both courses, the instructor can ask targeted “trace” questions. For instance: “Where do documentation skills introduced in Course 1 reappear in Course 2, and in what form?” or “Which communication objectives are reinforced, and which quietly disappear?”
Rather than generating new content, the tool helps surface patterns across the materials the instructor already uses. It can reveal where a thread weakens, where it duplicates unnecessarily, or where it never fully connects. The faculty member then decides whether the pattern reflects deliberate sequencing, curricular drift, or a true gap and what to change.
Based on those findings, the instructor might revise one workshop prompt, adjust one rubric line, or shift one assessment objective to restore continuity.
In this way, NotebookLM functions less as a drafting assistant and more as a mapping tool. It makes the curricular structure visible across courses, while interpretation, prioritization, and revision remain the faculty member’s responsibility.
Implications for Faculty Practice
As AI tools become more common, it is important to distinguish between tools that generate content and those that help faculty examine structure. NotebookLM does not make pedagogical decisions or evaluate learners. Instead, it allows instructors to trace how ideas move, persist, or fade across materials they already control.
For faculty responsible for multi-course sequences, being able to see where threads strengthen or unravel can make curricular coherence more visible. If a tool can help you map the continuity of reasoning skills from one course to the next, how might that influence the way you plan your next revision cycle?
*ChatGPT 5.2 (OpenAI) was used to assist with editing for clarity and concision
References:
1. Holmes W, Bialik M, Fadel C. Artificial Intelligence in Education: Promises and Implications for Teaching and Learning. Center for Curriculum Redesign; 2019.
2. Miao F, Holmes W. Guidance for generative AI in education and research. UNESCO; 2023. doi:10.54675/EWZM9535. Accessed March 9, 2026.
3. Samuel A, Soh M, Jung E. Enhancing reflective practice with ChatGPT: A new approach to assignment design. Med Teach. 2025;47(9):1438-1440. doi:10.1080/0142159X.2025.2461534.
4. Wiggins G, McTighe J. Understanding by Design. 2nd ed. ASCD; 2005.
Author Bio(s):
Stephanie J Counts is an Associate Professor at the Midwestern University College of Pharmacy-Glendale. Educational scholarship interests include educational technology, instructional design. In her free time, Stephanie enjoys building Legos.
Pulses is a scholarly blog supported by a team of pharmacy education scholars
Pulses 