TBR AI EXCHANGE
Submission Date
Submitter’s Name/Email
Institution/School
Department/Discipline
Activity Purpose (assessment, data collection, classroom management, etc.)
AI Tool(s)
Activity Details
One of the most practical ways I have used AI in my teaching is through the development of a master prompt for creating tailored lecture notes. This case study focuses on how a master prompt can help faculty transform existing course materials, such as PowerPoints and lecture transcripts, into organized, student-friendly, accessible, and D2L-ready lecture notes.
In many online courses, faculty already have strong instructional content. However, that content may exist in several different forms. A PowerPoint may provide the structure of the lecture, key terms, images, and major concepts. A video transcript may include the fuller explanation, examples, instructor voice, and informal clarifications that students would normally hear during a face-to-face class. The challenge is that neither source is ideal by itself. PowerPoints can be too brief for students to study independently, while transcripts can be too conversational, repetitive, and difficult to follow as written lecture notes.
To address this, I created a master prompt that tells AI exactly how to combine these materials into one polished set of lecture notes. Instead of asking AI to simply summarize a lecture, the master prompt gives clear directions about structure, tone, formatting, accessibility, and student usability.
A master prompt is a reusable set of instructions that tells AI how to complete a repeated task in a consistent way. Instead of writing a new prompt from scratch every time, the instructor creates one detailed prompt that can be used again and again with different course materials.
For faculty, a master prompt works best when it is connected to a task that repeats across modules, courses, or semesters. For example, an instructor might create one master prompt for D2L-ready lecture notes, another master prompt for course banners, another for quiz questions, and another for discussion prompts. Each master prompt gives AI the structure, expectations, tone, and format for that specific type of task.
For my lecture-note example, the repeated task is creating student-facing lecture notes from existing PowerPoints and lecture transcripts.
The purpose of the master prompt is to create a repeatable process for converting raw instructional materials into polished online learning content. The master prompt acts like a reusable instructional design template. Once the prompt is created, I can use it across multiple modules and courses by providing the relevant PowerPoint, transcript, or lecture materials.
The master prompt gives AI a consistent set of expectations. It tells the AI to use the PowerPoint as the structure for the lecture, use the transcript to add explanation and instructor voice, remove unnecessary repetition, define important concepts naturally, and format the final product for D2L Brightspace.
This helps prevent the AI from producing a generic summary. Instead, the AI creates lecture notes that are organized, readable, and aligned with the way I actually teach the material.
My process usually includes the following steps:
This process keeps the instructor in control. AI assists with organization, formatting, and cleanup, but I still make the instructional decisions. I review the final content, check disciplinary accuracy, and revise anything that does not match my teaching goals.
The master prompt instructs AI to:
This means the master prompt is not only about saving time. It is also about creating a consistent and intentional course-development workflow.
One of the most important benefits of this process is accessibility. In an online course, students should not have to rely only on PowerPoint slides or video lectures to access course content. Written lecture notes give students another way to engage with the material.
Creating lecture notes from PowerPoints and transcripts helps support students who may need or prefer text-based materials. This includes students who use screen readers, students who need to review content multiple times, students with unreliable internet access, students who cannot easily stream videos, multilingual learners, students with attention or processing challenges, and students who simply learn better by reading.
The master prompt also helps make the notes more accessible by encouraging clear structure. Instead of pasting a long, unorganized transcript into D2L, the final lecture notes can be divided into headings, short paragraphs, and lists. This makes the content easier to scan, easier to navigate, and easier for assistive technology to interpret.
Another major benefit is that the master prompt can be designed to create D2L-ready HTML. This is useful because formatting directly inside D2L can be time-consuming, especially when creating multiple modules across multiple courses.
The master prompt can tell AI to use clean HTML elements such as:
This matters because accessible formatting is not just about how something looks visually. It is also about how the content is structured behind the scenes. For example, using proper headings helps students navigate the lecture notes more easily. It also helps screen reader users move through the content by section rather than having to listen to one long block of text.
The master prompt can also help avoid common formatting problems. For example, it can reduce the use of overly decorative formatting, inconsistent fonts, large blocks of unbroken text, or confusing visual layouts. The result is a cleaner page that works better inside D2L Brightspace.
This process improves the student experience because students receive lecture notes that are more complete than a slide deck but more organized than a raw transcript. They can read the notes before watching a lecture, use them while studying for a quiz, return to them when completing assignments, or use them as a review tool at the end of the module.
It also helps create consistency across the course. When every module uses a similar lecture-note structure, students know what to expect. They do not have to relearn the organization of the course each week. This consistency can reduce cognitive load and help students focus on the actual course content.
For faculty, the process reduces repetitive labor. Instead of manually reformatting lecture material for every module, I can use the master prompt to produce a strong draft in the correct format. I still review and revise the material, but the most time-consuming parts of cleanup and formatting are reduced.
The instructor’s role remains central. I am not using AI to replace my teaching or make decisions about what students need to learn. Instead, I am using AI as a support tool to help transform my existing teaching materials into a more accessible and usable format.
I still decide what content belongs in the lecture. I still check the accuracy of the final notes. I still revise the language, examples, and organization when needed. The master prompt simply gives me a more efficient and consistent way to prepare course materials for students.
This is an important distinction. The value of the master prompt is not that it removes the instructor from the process. The value is that it allows the instructor to focus more on content quality, student learning, and course design rather than spending excessive time on formatting and cleanup.
Creating a master prompt is a process of designing a reusable set of instructions for a repeated teaching task. The process can be broken into several steps.
The first step is to identify a task that I do more than once. A master prompt is most useful when the task repeats across modules, courses, or semesters.
Examples might include:
For my lecture-note example, the repeated task is creating student-facing lecture notes from existing PowerPoints and lecture transcripts.
Before writing the prompt, I need to know what I want the final product to be. This includes the format, structure, length, tone, and purpose.
For lecture notes, I want the final product to be:
This step matters because AI needs clear direction. If I do not know what I want the final product to look like, the AI will make more of those decisions for me.
Next, I identify what materials the AI should use. A strong master prompt should tell AI what sources matter and how to use each source.
For lecture notes, the source materials may include:
The master prompt should also explain the role of each source. For example, in my lecture-note workflow, the PowerPoint gives the structure and sequence of the lecture, while the transcript provides fuller explanation, examples, transitions, and instructor voice.
This prevents the AI from treating all sources the same way. It also helps the AI combine materials more thoughtfully.
A strong master prompt tells the AI what role to take. This helps shape the kind of response it gives.
For example, I might tell the AI:
Act as an instructional design assistant helping create accessible, student-friendly lecture notes for an online college course.
This is more useful than simply saying, “Summarize this lecture.” It tells the AI that the goal is not just summary. The goal is course design, student learning, accessibility, and online readability.
The next step is to write the central instruction. This should be direct and specific.
For lecture notes, the main task might be:
Create D2L-ready lecture notes using the PowerPoint and transcript provided. Merge the two sources into one clear, organized lecture for students.
The main task should tell AI exactly what it is producing.
This is one of the most important parts of a master prompt. The prompt should explain what should remain the same every time the prompt is used.
For lecture notes, the consistent elements might include:
This is what makes the prompt a “master” prompt rather than a one-time prompt. It creates a reusable pattern.
A master prompt should also make room for customization. I need to identify which parts of the prompt will change depending on the course, module, or assignment.
For lecture notes, the changing elements are usually:
One way to make this easier is to use brackets in the prompt, such as:
This makes it clear which parts should be replaced each time.
If the final product needs to work in a specific system, such as D2L Brightspace, the master prompt should say that clearly.
For example, for lecture notes I include instructions such as:
Format the final output as clean D2L-ready HTML. Use appropriate HTML structure, including headings, paragraphs, lists, bold text, italics, and horizontal rules where useful. Keep the formatting simple, accessible, and easy to copy into D2L Brightspace.
This is important because D2L formatting can be time-consuming. If the prompt tells AI to produce clean HTML, I can copy and paste the final result into D2L more easily.
Formatting instructions can also support accessibility. For example, the prompt can tell AI to use headings in order, avoid large blocks of text, avoid decorative formatting, and create content that works better with screen readers.
A master prompt should not only tell AI what to create. It should also explain how the final product should support students.
For lecture notes, I can include accessibility expectations such as:
These instructions help the AI produce materials that are easier for more students to use. This is especially important in online courses, where students may rely heavily on written materials.
A good master prompt also includes boundaries. These prevent the AI from adding things I do not want.
For example, in my lecture-note prompt, I might say:
These boundaries help the AI avoid common mistakes.
After writing the first version of the master prompt, I test it with one module or one example. Then I review the output carefully.
I ask questions such as:
Testing is important because the first version of a master prompt usually needs revision. The prompt improves as I see what the AI does well and where it needs more direction.
After testing, I revise the master prompt. If the AI produced notes that were too brief, I add instructions for more explanation. If the AI added a glossary I did not want, I add a sentence telling it not to create one. If the HTML was too complicated, I add instructions to keep the formatting simple.
This is an important part of the process. A master prompt is developed through trial, review, and revision. It becomes stronger as the instructor identifies what works and what needs to be more specific.
Once the master prompt works well, I save it so I can reuse it. I can keep it in a document, a notes file, or another location where I can copy and paste it when needed.
I also label the prompt clearly. For example:
Saving the prompt makes the workflow repeatable. It also means I can continue improving the prompt over time.
Once the master prompt is saved, I can reuse it by attaching or pasting new source materials. I may only need to change a few details, such as the module title, topic, or special instructions.
This is where the time savings become clear. I am not starting from scratch each time. I already have a tested set of instructions that reflects my teaching style, course needs, accessibility expectations, and D2L formatting requirements.
The final step is always instructor review. Even with a strong master prompt, AI output should not be copied into a course without checking it.
I review the final product for:
This keeps the instructor in control of the course. The master prompt helps create the draft, but the instructor makes the final decision about what students see.
A reusable master prompt for this process could look like this:
Create D2L-ready lecture notes using the PowerPoint and transcript provided. Merge the two sources into one clear, organized lecture for students. Use the PowerPoint to guide the structure, sequence, and major topics. Use the transcript to add explanation, examples, transitions, and instructor voice. Clean up the transcript by removing filler words, repetition, false starts, rambling, and distracting tangents. Preserve the instructor’s conversational teaching style when it supports student engagement, but make the final notes professional, readable, and student-friendly. Explain important terms and concepts naturally within the lecture where they first appear. Do not create a separate key terms section, glossary, quiz, or summary unless specifically requested. Format the final output as clean D2L-ready HTML. Use appropriate HTML structure, including headings, paragraphs, lists, bold text, italics, and horizontal rules where useful. Keep the formatting simple, accessible, and easy to copy into D2L Brightspace. Do not include unnecessary decorative formatting. Do not include commentary before or after the HTML.Using a master prompt for lecture notes has several benefits:
Overall, this case study shows how a master prompt can support thoughtful and responsible AI use in teaching. The master prompt gives the AI structure, but the instructor provides the expertise. The result is a more efficient course-development process and a better learning resource for students.
For TBR, this is an example of how faculty can use AI in a controlled, practical, and pedagogically meaningful way. A master prompt can help faculty create accessible, consistent, and student-centered course materials while still maintaining academic oversight and instructional quality.
The AI does not decide what my course should be. Instead, the master prompt helps me direct the AI so it supports my instructional goals, saves time, improves formatting, and creates more accessible materials for students.