The challenge
An undergraduate in Principles of Marketing works through an assignment at midnight. A graduate student in the online M.S. in Digital Marketing program checks a course policy before a deadline the next morning. Their professor would otherwise be the one answering both, across six different courses, whenever she found the time.
Her courses are fully asynchronous, so a student could be working at any hour, on any day. The answer to a question almost always existed somewhere, in a syllabus, a reading or an assignment brief she had already written, but reaching it meant email, Zoom, phone or D2L chat, and a wait until she was available.
A generic assistant trained on nothing in particular would have been no better than a search engine. What she wanted was something that knew this exact course and answered the way she would.
The solution
Six assistants, one per course. Two for sections of Consumer Behavior, and one each for Social Media, Principles of Marketing, Special Topics in Digital Marketing, and Digital Marketing Ethics. Each is grounded in its own course’s materials rather than a shared pool.
Embedded where students already look. Each assistant is pinned to the top of its course’s D2L announcements page and placed inside a course module, so nothing new had to be adopted or learned.
Configured to sound like her, not like a bot. Each one is tuned to feel like an extension of the course, consistent with how she presents material in class.
Updated the way she updates a syllabus. She reviews each assistant before the course begins and re-uploads materials by hand whenever something changes, which keeps the person who knows the course in control of what it can say.
The requirements
Five things Dr. Price-Rhea would not compromise on. It had to sound like her, not generic. It could not replace her as the instructor. It had to require no technical setup. Materials had to stay current on her own schedule. And students still had to be able to reach her directly.
Those five rule out most of the market between them. An assistant that needs an engineer fails the third. One that routes students away from their instructor fails the second and the fifth. One that speaks in a vendor’s register fails the first on the opening line.
The capability that decided it
What decided whether this worked was not a technical feature so much as how much she could shape each assistant’s tone and approach, unaided. She did not want an assistant that gave generic answers. She wanted every one of them to feel like an extension of the course, consistent with how she presents material in class.
Building that took nothing more than her own course materials and time spent testing and refining. A professor with more than twenty years of teaching behind her already knows how she wants a concept explained. The work was getting that into the assistant, and she could do it directly, without writing a line of code.
The results
One instructor built and has maintained six separate assistants, spanning both undergraduate and graduate courses, with no developer or IT involvement at any point. Each continues to run on course materials she reviews and updates herself, semester after semester.
In her words: “The assistant gave them a place to start using the context and guidance I had provided while I remained available as their instructor when they needed me. That was especially valuable in an online learning environment, where students may be working on coursework at very different times of the day. It also had the potential to reduce some of the repetitive, routine questions that naturally occur in a course, allowing my interactions with students to focus more on discussion, clarification, and the kinds of questions where my experience and judgment as the instructor mattered most.”
The boundary in that account is the part worth noticing. The assistant handles the first layer and she stays available for everything past it.
Why it worked
No developer required. Building an assistant took only course knowledge, so the person who knows the course could build it herself.
A voice, not a script. Each assistant’s tone and approach could be shaped directly, so it reads as an extension of her teaching rather than a generic chatbot.
It lives where students already are. Embedded in the existing D2L shell, so nothing new had to be adopted or learned.
It stays current without a release cycle. Materials are reviewed before each course begins and re-uploaded by hand, on the instructor’s own schedule.
| Measure | To date |
| Personal AI teaching assistants, one per course | 6 |
| Students reached in a typical semester | ~100 |
| Developers or IT staff involved | 0 |
| Faculty member behind every voice | 1 |
| Course sections covered, undergraduate and graduate | 6 |
Figures reported by Dr. Kelly Price-Rhea, East Tennessee State University, from her own account of building the assistants.
