Transforming Education with AI: Custom GPTs & Bots at Northeastern University | OpenAI Academy
A tour of custom classroom GPTs, an AI-assisted cancer nanomedicine textbook, and a learning-by-doing philosophy built at Northeastern University, made for the OpenAI Academy series on professors teaching with AI.
Getting funding approved at a university can take a year for even a small project. Building a custom GPT for an entire class, by contrast, takes about half an hour and costs one GPT Plus subscription. That gap between institutional pace and what a single motivated instructor can build alone is the real subject of this OpenAI Academy submission, a fast tour through the AI tools reshaping how courses are taught at Northeastern University's College of Engineering.
Made for OpenAI Academy's "Professors Teaching with AI" series, the video is deliberately a show-and-tell rather than a comprehensive catalog. There are hundreds of AI projects behind the scenes; this is a walk through a handful of them, chosen to demonstrate what building with AI, and having students build with AI from their first day on campus, actually looks like in practice.
Custom GPTs built in an afternoon
The centerpiece of the demo is a set of custom classroom GPTs, each built around a written prompt rather than custom code. Three examples get walked through in detail. ADA is an introductory calculus bot used in Abby Williams's class, originally written in about an hour and since taken over and refined by Abby herself, who tuned its tone to be encouraging even when a student gets something wrong: pointing out what was done correctly before explaining the error, rather than just returning a flat right-or-wrong answer. Nuke is an introductory physics bot used in classes taught with colleagues Shri and Tom Kelly. Grace supports a Coursera algorithms course, and its effect on office hours has been dramatic. After introducing Grace, office hours attendance dropped to nearly nothing within the first week, students found they could get their questions answered through the bot instead, a shift that shows up clearly in usage statistics.
Student feedback on these bots has averaged around 4.8 out of 5 in surveys. One story stood out: a student in Abby's class who had math anxiety and was afraid to ask questions in person for fear of feeling stupid found she was comfortable using the bot instead, since it gave her the scaffolding she needed, explaining why an answer is right or wrong, without any of the social pressure of asking a professor face to face. The video also shows ADA handling a handwritten calculus problem, since students often work equations out on paper before photographing them, and demonstrates the bot walking through what was done correctly and where a small, specific error crept in.
Botspeak and computational skepticism
Two frameworks anchor the broader teaching philosophy. Botspeak is an AI fluency framework the team has developed to help students learn how to work productively with AI tools rather than just use them passively. Computational skepticism, embodied in a project called Popper, is a set of automated tools that check and provide evidence for whether an AI-generated claim is actually true, treating that verification step as essential rather than optional, since what a language model returns is not automatically correct.
Writing a textbook with AI as a drafting partner
One of the more ambitious projects described is an extensive textbook on cancer medicine and nanomedicine, developed with physics professor Shri and led primarily by a collaborator named Aan, intended to make this material accessible to people in places where books and specialist training are hard to come by. Language models are used to produce first drafts of chapters, a process that still takes a few months per book even with AI assistance, but that would likely take a decade without it. Because each chapter contains hundreds of individual factual assertions, the Popper verification tools are used to search the web and gather evidence for specific claims, automating what would otherwise be an enormous manual fact-checking burden.
Once a draft exists, a separate tool called Medhavy turns it into what's described as an intelligent textbook: a reader logs in, and the book presents itself differently depending on who they are, a physician might be led through the material on a different path than a high school student encountering cancer nanomedicine for the first time.
A glimpse of what else is running
Running short on time, the video closes with a rapid list of other active projects rather than deep explanations of each: Dayhoff, focused on protein prediction and computational biology agents acting as research labs; Madison, which extends standard reinforcement learning into agentic AI applied to branding and marketing; and work applying the Raman effect and spectroscopy to wastewater surveillance for public health monitoring. There's also Lyrical Literacy, a project using AI to generate songs as a learning tool for people whose brains process information differently, built on the premise that not everyone learns best by reading text.
Key takeaways
- Custom GPTs can be built by a single instructor in roughly half an hour to an hour and deployed to an entire class, sidestepping the slow institutional funding process that formal tools usually require.
- ADA (calculus), Nuke (physics), and Grace (Coursera algorithms) are three classroom bots in active use, with survey ratings averaging around 4.8 out of 5.
- After adopting a course bot, in-person office hours attendance can drop sharply within the first week as students shift to asking the bot instead.
- Popper, the computational skepticism framework, automates evidence-gathering to verify individual factual claims inside AI-drafted material, including textbook chapters.
- AI-assisted drafting cut the writing timeline for an extensive cancer nanomedicine textbook from an estimated decade down to a few months.
- Medhavy adapts how a finished textbook is presented based on who is reading it, tailoring the path through the material to the reader's background.
Who this is for
This is aimed at educators and administrators weighing whether AI tools belong in a college classroom, and at students curious what "learning by doing with AI" looks like in a real engineering program. Much of what's shown, including the Botspeak fluency framework and the Lyrical Literacy project, runs through Humanitarians AI, the nonprofit behind this work, which publishes tutorials and code for anyone who wants to build similar tools themselves.
Full transcript(auto-generated, with timestamps)
[0:00]Hey, uh my name is Nick Bear Brown. Uh Open AI asked me to talk about uh the educational AI we do here at Nor Eastern plus my nonprofit humanitarians AI. I'm a professor of engineering at Northeastern. Um what Open Eye asked me to talk about is what we teach, but we have hundreds of AI projects. So I'm just going to do a showand tell for a couple, not hundreds. But this is why I made this web page here. Um, I'm going to quickly go over what we built mostly just show and tell for the how we built it. I made this web page here so you can come to
[0:39]This web page. We have other tutorials. We have GitHub. We have a nonprofit humanitarian AI that can help you build it. But this focuses on what we build. We build a lot of things and we do it by doing it with AI. You basically build it and see what happens. So, we're going to talk about some angic AI systems we built. Uh, we're going to talk a little bit about an AI fluency framework called Botspeak that we have. We're going to talk about some things we've done for Nor Eastern, just a hod hodgepodge of uh educational tools that we built. We have a wonderful project called lyrical
[1:14]Literacy, which is using AI to create songs for people who learn in different ways because everybody's brain is different. We have a lot of people just building things for good causes because you learn by doing. So we'll talk a little bit about that. We have the computational skepticism framework. What this means is uh we have tools which automatically look and check and give evidence for whether something is true or not. It's a big deal. AI is what it's returning right. Uh we do a lot of the tutorials including tutorials on how to do everything that I'm talking about here. And we do research and publications. Uh I've done a ton of
[1:51]Courses so I won't go over them. Uh again we have a humanitarian AI which is a nonprofit which does this as well. We believe learning doesn't stop when you graduate. So until a recent graduate gets a great job, they continue learning and doing. Even a graduate who graduated two years ago, a year ago, there's AI courses which simply did not exist when they graduated two years ago. So they'll come back and upskill and learn as will mid-career people with humanitarians AI. We also have a group of AI skunk works. We believe you should start building the first day you're on campus. Just build things, do things, learn by doing. And
[2:29]I've won a bunch of awards on this. So, let's get going. I'm just going to do a show and tell, show some of our projects. We've created hundreds of custom GPTs. They're super easy to create and they're really effective. What's beautiful about the custom GPTs is if you've ever worked in an educational institution, getting the money to fund anything is virtually impossible. it can take you a year to just get a little bit of money to fund something. But with the uh custom GPTs, all you have to do is create them. If one person has a uh a GPT plus account, they can create a
[3:10]Custom GPT for hundreds of students in the class. So, it takes the custom GPS are super si simple to make. Basically, you give up prompts and for all of these GPTs here, uh, we put all of the actual exact prompts that we use. So, these are the prompts using ADA. So, this is ADA, an introductory calculus bot that's used by Abby Williams in her class. All of these bots I'm going to talk about, I'm just going to talk about three. We have hundreds of them. I'm going to talk about um Nuke which is a physics bot intro introductory physics bot that's Tuesday at North Eastern for the
[3:47]Introductory physics classes with Shri and Tom Kelly. Um Grace which is for my uh Corsera algorithms course after using Grace in my Corsera algorithms course I just don't have people come to office hours anymore. Everything gets answered through the B. I mean the first week maybe a couple people come but after that people just using the the chatbot to answer everything and we can see that from the usage statistics and from you know the fact that people stop coming to office hours and ADA is for introductory calculus. So here are the prompts super easy it takes about half an hour to make these things we have some data uploaded these Abby
[4:30]Has taken over writing this bot. So basically we wrote this uh Dev Shaw and I wrote this initially and then uh it took maybe an hour to write the bot. Students love it. Uh we've put some uh surveys on these. They average around 48 out of five for all free bots. And what's nice about it is Abby told me that one of the students came up to her who had math there. She was afraid to ask Abby questions because she would feel stupid. but she uses the bot. Okay, so let's try Atta with a handwritten problem. I'm told by Abby that often in calculus people write equations on
[5:11]Pieces of paper and then upload you know what they take from their camera uh because math is sometimes hard to write in a proper way. You don't know latte or other things. So let's go ahead and try that. So, we're going to upload just a little handwritten um so this may or may not be right and we're going to ask added to check it. What every teacher wants is they want scaffolding. They don't want the answer to be spit out. They they want if it's right, why is it right? If it's wrong, why it's wrong. And what's also beautiful about this is uh tone. Navy's very friendly and so she
[5:55]She took over prompting it. She wants it to be encouraging even when you get things wrong. What you did right, what you did wrong. So this this has this, you know, this is not correct, but you got this part right. So good job on getting this part right, but you made a sort of a trivial little error here and it would be correct only if you made this change. This is very much happening. is very much the tone of yeah, you got it partly not you are wrong but you're sort of right but you know you you made a mistake here and so not only is it very useful these tools
[6:28]But it even has the sort of a tone of Abby in the GPT where it's encouraging and friendly even when you make a mistake. So that's it for this and we'll go on to the next show and tell more show and tell. Uh we use uh language models to write first drafts of books. This is an extensive book. Uh this is working with Shri and Aan and Shri is a distinguished professor of physics here with nanome medicine at northeastern and uh for his canare program canare program teaches cancer medicine and nanom medicine to people all around the world even very sort of places where it's really hard to access books and
[7:16]Things like that. So Aan primarily is leading this project. We wrote a lot of tools to help write this book with prompts to get a first draft and then once we have a draft of a book, a book like this is huge. I don't think this book gets written if it's not for AI helping us write this book. It's a very extensive book and just getting a first draft of this book is taking a few months using the AI tools, but it's an important book I think. And um the language models help us write drafts of chapters. Further the popper uh program what it's doing is each one of these
[7:54]Chapters has hundreds of assertions. You know where did you get evidence for this? Where do you have evidence for this? Where do you have evidence for this? And so we also have tools which go search the web use the language models to help us things like the the GPT 40 model to gather what is the evidence for you know this being a tumor suppressor. what is the evidence for that and automate that whole process. I don't think a book like this gets written if not without the help of AI. It'll take us months to write this. It's an extensive book. This could take a decade
[8:27]Easily to write pre AI. Um in order to actually view the book, just reading the table of contents is a chore. We've also created uh Madavi which is an intelligent textbook and what it allows you to do is it allows you to log in tell who you are and it'll present the book to you according to who you are. So if you are a physician, it might lead you in the book in a different path than you would be if you're a high school student wanting to learn about cancer or cancer nominal medicine. But I don't think this book gets written if it's not for the help of tools like JBT and other
[9:06]Language bonds. Okay, my timer says I'm out of time, which kind of makes me want to cry because we have so many more things to show you related to what we do with AI. We have day off which is we're doing a lot of stuff with uh protein prediction and agents for uh doing computational biology and acting as research labs. We have popper which is computational skepticism which is automated tools to verify whether AI is right or not. We have Madison which are some extended uh reinforcement learning engines which extend a standard reinforcement learning model to angenic AI with branding and marketing. Um we have uh ramen effect which is uh
[9:48]Agents to wastewater um Sears um Ron and spectroscopy for uh public health. But I'm out of time so I'll just leave you with do it. If you want to do AI just do it. Humanitarians AI here will help you do it. Everything I've talked about we have on the website YouTube and GitHub for code. Just do it.
More videos
2:08Bridging the Pixel Gap in Browser Automation.
2:23How One Narrow Safety Rule Can Make an AI Less Safe Everywhere Else.
2:04Why splitting a chunk from its document makes it retrieve for the wrong question
4:20Three You Can Take Back. One You Can't.
2:21Why a 50-turn agent pays for the same screenshot 35 times unless it caches the pixels
1:53