Dear Student,

I’m sipping coffee as I write this—a very teacherly thing to do. I make it in my own 16-ounce thermos each morning, grinding beans that I get from a local roaster, stuffing them into a stainless steel pod for the Keurig, then adding raw cream and 2½ teaspoons of sugar (the ½ makes me feel indulgently quirky). Or, if I’m away from home, I’ll splurge on the largest sized cappuccino from the most hipster coffee shop I can find nearby. Often they’ll ask if I want to add flavoring, and I’m tempted to lecture poetically:

“Do you realize how wrong it is to mask the most extraordinary flavor Mother Nature has ever created with a lab-produced, artificial trick?”

But I tamp down the impulse to berate the barista. Instead, I smile and shake my head no and tell them I love the OG, thanks anyway.

Well, as a teacher and a writer, I have multiple objectives behind every choice I make, whether in the classroom or on the page, so let me elucidate.

1. I want to show you me. Some of you might be in my class and have witnessed me lovingly cradle my thermos between two hands throughout each lesson; many of you will never meet me; others might need to check the name at the top to know which camp you’re in. Whatever the case, I believe you’re more likely to hear me out if I exhibit some personality.

2. I have comparisons to make between coffee and writing and chatbots that I’ll get to in a bit. (Astute readers may have guessed some from my title and intro, but I also hope to surprise you.)

3. I want you to know immediately that a human is writing this.

A chatbot has never tasted coffee and never will. It will never experience the warm rush of creamy bittersweet liquid flowing between its lips and over its tongue and down its throat; it will never feel the fabulous buzz of caffeine that brightens even the gloomiest outlook; it will never know the horrific daily letdown of lifting the mug that final time to discover there are no more sips to be had. Coffee (or whatever your favorite beverage may be) is a uniquely human experience, so if I ask a chatbot to write about it, all the bot can do is fake it.

Artificial Flavoring

I want to give you a taste of what I mean here, so I asked the chatbots kindly (because we have an odd tendency to be polite to robots), “Please write me a short poem about how amazing coffee is.”

ChatGPT spit out this:

Gemini prepared an identical structure, as if two quatrains (four-line stanzas) are the standard for “short poem”—and even copied the same ideas, like ending with calling coffee a friend, alerting us that nothing very original is happening here:

Some of these lines might be kinda cool. They might sort of mimic my experiences in a way that makes me smirk a bit. But something crucial is missing.

I’ve tried getting bossier with the bots, suggesting the language should feel more contemporary casual or the imagery grittier or the literary devices more unexpected or whatever else I can pinpoint that I love about real poetry. They will apologize and ask for another try. None of their attempts get any closer to having what a bot can’t have: originality.

What We Value in Being Human

Real poems are made of experience and emotion, not predictive rhyming text. In fact, when writing a poem, I reject most every predictable word that comes to mind—what I crave are new combinations of words / feelings / spells that will have my reader thinking, Ooooh yes, THAT. It will tether us as humans to a shared familiarity in which we are less alone because some other person has felt and described what we have also felt.

And of course the need for that humanness is not limited to poems. In this essay I am keenly aware of wanting every sentence to feel real—with words like kinda or ooooh—because I want to connect with you.

So one question to ask ourselves is this: If a chatbot by its very nature (haha) cannot have the essential qualities necessary to write like a real human, why and when and how would we want to use it?

Well, one answer is that not every type of writing needs to be poetic or personal or even human sounding. Wanna know when I absolutely let the bots have at it and write the whole thing for me (i.e. when I cheat)? Rubrics—those tedious-but-somewhat-necessary evaluative breakdowns of how I’m gonna grade your essay. Do I need to sit there and come up with each mind-numbing iteration of what an A vs. a B vs. a C looks like for each criteria? Emphatically, NO. I don’t. It’s not gonna make me a better writer. It’s not gonna connect me more to my students. It’s just a non-personal writing task that needs to be produced as quickly as possible so we can all move on with more important human endeavors.

This is a crucial distinction: I want you to value your experience and emotion and time and effort and beautiful humanness so much that you make wise decisions about when the chatbot is the right resource for the job and when it’s not.

• Is this a piece of writing that needs to sound authentically human and connect with your audience emotionally?

• Is it something that is naturally more robotic anyway and letting a bot handle it would free you up to enjoy being human?

• Is it permissible/ethical (according to your teacher, your boss, your audience, or your own conscience) to use AI for that task?

Banned Bots Are Like Life Without Coffee

Okay, this analogy is weaker for sure, since I would easily give up chatbots before giving up coffee, but I do have a big comparison to make here: I grew up in a religion that did not allow coffee, just like you might have gone to a school that did not allow chatbots.

As a kid, I tasted mocha ice cream and became instantly obsessed with its one-of-a-kind flavor—but felt absurdly guilty because I didn’t know how broadly the religious coffee ban applied. For many many years, I steered clear of anything labeled coffee / mocha / java / espresso or even tiramisu, just in case. It wasn’t until well into my adulthood that I left religion behind and decided on my own rules for myself. Maybe now you can understand why my fondness for coffee is so intense after being denied it so long, like a star-crossed love affair!

A big part of my exigency and purpose in writing this article is to respond to the all-out chatbot ban that’s happened in many schools where the concern over cheating has outweighed the rest of the conversation. To me, this is equivalent to abstinence-only sex education: if all you teach students is not to do something, they get zero training on how to be smart about doing the thing they’re likely to do anyway.

Not only are you likely to use it on your own, but you’re also likely to need to use it in the future. A 2024 article in Information Systems Education Journal argues, “Students should be empowered to use AI, and knowing when to do so is a critical first step. It is essential that they learn about these tools to be competitive in their fields of employment” (Firth). After all, technology advancements tend to be quickly integrated into professional settings rather than avoided.

I’ve definitely strained my coffee metaphor here (pun intended), but I want to make this crucial point that, even though a bots’ writing is like cringey artificial flavoring, it has its uses. Some of those uses are actually awesome. Some of those uses can help you become a better student / writer / professional / person. And we’re gonna miss out if all we do is ban them.

However, you’ll still need to bow to the rules of your institution and/or your professors/employers. Check the policies to be sure of what they consider to be appropriate AI usage before you dive in. In my classes, I tell my students that cheating has the same definition to me whether you use a person or a bot: if they do the work for you, that’s wrong; if they assist you like a writing tutor, that’s great!

Chat to Learn and Learn to Chat (vs. Cheat)

“We should get coffee and catch up sometime!” is the best sort of invitation, isn’t it? It’s an offer of connection—that vital ingredient for healthy humaning.

In my opinion, conversation is also one of the things that draws us toward programs like ChatGPT. I mean, it’s literally in the name! There is something great about a dialogic exploration where two contributors offer each other questions and answers that can lead to new discoveries. When they’re both human, they learn more about each other—how the other person thinks or feels or lives or dreams—as well as gaining insight into whatever topics arise. When one is a bot and one is a human, both are still learning. The bot is constantly updating its memory, learning more from you about what humans want and how we combine words; you can likewise uplevel your writing if you watch for what you can learn from the bot.

In fact, approaching AI interaction this way—looking for how it can enhance your own thinking process—helps to combat some legitimate objections to chatbot usage. As Julia McKenzie Munemo, the writing center director at Williams College, warns students directly,

We’ve come to see the goal of writing as getting to our point quickly, making a strong argument and concluding carefully, all with perfect grammar and syntax. But anyone who has revised a paper, come back to an idea after a sleep or a walk or a shower, or worked with a tutor to brainstorm new directions will tell you that the true goal of writing is to clarify, understand and experience our own thinking.

The Bot will steal that from you. If I could send one message to students, it would be: don’t let it.

I completely agree with her. Don’t let it do your thinking for you. Don’t let it steal the process of finding your clarity and determining what it is that you have to say. But what if we can learn to chat in ways that make us better thinkers?

In class, I have my understandably chatbot-skittish students (they’re much like younger me trying mocha ice cream, unsure it’s allowed) start with a very simple conversation:

This is so very very different from those emotionless poems I had the chatbots spit out. The emotion in the classroom becomes audible as students exclaim, “Wait, what? How does it know that about me just from one paragraph?” And unlike the copycat nature of the chatbot poems, no two students get the same feedback.

They get excited to keep talking to the bot. What else can you tell me about my writing? they wonder. They pop in extra samples. They’re curious and engaged. They’ve suddenly realized that the inconceivably enormous amount of human writing the chatbot has analyzed means it has something ironic to offer us: enhanced connection to ourselves.

I’ve noticed that this simple new awareness of their own writing qualities has led my students to embrace more of their humanness in their writing. They can see more clearly what distinguishes them from a robot, so they lean into their own real voice rather than trying to sound “smart” with words they don’t actually use IRL. When I read their essays, I don’t have to worry they cheated: the writing sounds more like them than it did before they chatted with the bot.

I’m not the only one who’s observed the value of this type of dialogue. A 2023 article in Language Magazine asserts that gifting students more personalized feedback is one of the most positive potential aspects of using chatbots in education. Chatbots can benefit students with “immediate feedback on various areas of writing since [chatbots] process and respond to a text at near-lightning speed” (Baffour, emphasis added). No teacher or writing tutor is superhuman enough to compete, so this is an arena where we should be welcoming the help.

And honestly, as a writing teacher, I wish I had the time to sit down one on one with every single student over coffee for an hour and tell them what I see about their writing. I frantically type as much response as I can when I grade a hundred essays per batch, but here is a chance for them to get a much greater quantity of personalized attention than they could possibly get from another human being.

It’s equivalent to being able to chat with a professor-like tutor over coffee any time you want, and at any stage of the development process. As college-comp gurus Gerald Graff and Cathy Birkenstein say in their latest edition of They Say / I Say,

These sophisticated bots can also help you overcome that dreaded feeling of writer’s block, and keep you company during a long slog of writing, breaking through the isolation of the writing process and offering stimulating feedback that can sharpen your focus—even at 2 o’clock, if it suits you, in the morning. (299)

How ironic that they used phrases like “stimulating feedback” and “sharpen your focus”—just like a burst of caffeine when you’re feeling sluggish!

Place Your Order

If you’ve ever gone to a coffee shop, you know how crazy specific the potential combinations of options can be. Not only do we have the basic menu choices like drip coffee, cappuccino, mocha, or latte, but we also tell them hot or iced, whole milk or almond milk or oat milk, 8oz or 12oz or 16oz, and we can customize further with secret additions that often aren’t listed.

With a chatbot, you get to—and need to—do the same.

Let’s say you’re working on an essay about the uses of chatbots in writing an essay. If that’s all you tell the chatbot, it might very well churn out an essay about the uses of chatbots in writing an essay, and you might suddenly panic because it just cheated even though you didn’t mean to ask it to do that! On the other hand, if you get as specific as a coffee order, you’ll automatically be in better shape:

When I fed this to Gemini, it gave me specific bullet points rather than an essay:

• Brainstorming and Idea Generation
• Research Assistance
• Writing Support
• Language Learning
• Peer Review and Feedback (“What are examples?”)

Each of these came with a detailed paragraph summing up how it could work. I then compared that to a human-written source: an article by Sabrina Ortiz entitled “5 Ways ChatGPT Can Help You Write Essays” that lists suggestions I’ve paraphrased here:

1. Generate topic ideas
2. Create an outline
3. Find potential sources
4. Make a sample essay as a guide
5. Catch editing errors

Notice, by the way, that finding potential sources is one of the ideas for chatbot help, and it easily could’ve been the case that I learned of Ortiz’s article via Gemini. Great! Just make sure that you go to the source itself, confirm that it’s real (yeah, bots can sometimes “hallucinate” and make things up), and compare/contrast the source info to what the bot offered. In this situation, both lists are valid; in other situations, you might discover the chatbot has told you something inaccurate.

Hopefully you can see the many advantages of using both chatbot and human-generated content. Gemini was quick to offer a similar “opinion,” which I found amusing:

It’s important to remember that chatbots are a tool, and they should be used in conjunction with other resources and human interaction. Students should always take the initiative to research, think critically, and develop their own ideas. Using chatbots responsibly can enhance the writing process and help students produce better essays. (“What are examples?”)

Well said, Gemini! So I decided to quote it and cite it to give the chatbot credit—and to model MLA 9 chatbot citations for you (which I recommend peeking at in my Works Cited section).

I’ve also had my students give the chatbot boundaries such as telling it to ask them questions to strengthen their thesis or give them suggestions for revision. This helps the chatbot understand its role in the conversation and lets the student retain autonomy over how to utilize the conversation. For example, when I had finished drafting this essay you’re reading, I fed it to ChatGPT with this detailed prompt:

It did just what I asked, and I was able to think over the feedback to decide how to improve my draft. I also sought out human feedback as well—some of which overlapped with the chatbot’s suggestions and some of which was very different, since humans have actual personality-based opinions that make interactions more interesting. As Gemini said, chatbot and human resources “should be used in conjunction”—instead of consenting to a complete robot takeover.

Get What You Want or Take It Back

Sometimes after you’ve ordered coffee, you take your lidded cup all the way to a cute little bistro table in the corner by the sunny window, hang your jacket on the back of the chair, settle in with your book or laptop or human friend, take your first sip … and realize they accidentally gave you a dirty chai or an Americano or a macchiato or any other menu possibility that was not what you ordered.

Sure, you could drink it. Or … you could take it back to the counter and ask again for what you actually wanted.

This is a key step in talking with bots. Too often my students just accept what the bot gives them when it isn’t what they wanted! The student might feel like the bot knows better than they do. Nope. The bot is guessing what you want based on what thousands or millions of other users have asked for, but those other users aren’t you. Just because a pumpkin spice latte is what most customers are ordering in October doesn’t mean it’s what you were craving that morning.

Remember that this is your order—that you are the one giving the orders around here! As Graff and Birkenstein insist, “Students themselves need to take the lead, mentoring, directing, and often even correcting the chatbots themselves” (298).

• If the bot tries to take over and write or rewrite your paper for you, you can redirect it: “Actually that’s not what I’m looking for. Can you just give me suggestions for how to revise the writing myself?”

• If the bot spits out huge amounts of text when you wanted less, you can say so: “Thanks but that’s way too much at once. I’m overwhelmed by it. Can we just go one step at a time?”

Once you get the hang of this, it becomes easy to remember that “the customer is always right”—and you are the customer.

Savor Your Humanness

There are far more ways to put chatbots to great use than I’ve listed here. In fact, the chatbots can tell you plenty more options much more efficiently than I can! Instead, my intention was to offer what the chatbots can’t: a very human perspective on how to write like a human—with a robot’s help.

I figure maybe the best thing I can leave you with is a poem I wrote myself:

Works Cited

Baffour, Perpetual. “AI Can Strengthen Student Writing, Not Weaken It.” Language Magazine. 25 Jan 2023. Web. 25 Oct 2024. https://www.languagemagazine.com/2023/01/25/ai-can-strengthen-student-writing-not-weaken-it/

Firth, David R., Mason Derendinger, and Jason Triche. “Cheating Better with ChatGPT: A Framework for Teaching Students When to Use ChatGPT and other Generative AI Bots.” Information Systems Education Journal 22.3, July 2024. pp. 47–60.

Graff, Gerald and Cathy Birkenstein. They Say / I Say. 6th ed, Norton, 2024.

Munemo, Julia McKenzie. “A Message to Students About ‘The Bot.’” Inside Higher Ed. 22 Jan 2023. Web. 25 Oct 2024. https://www.insidehighered.com/views/2023/01/23/message-students-about-%E2%80%98-bot%E2%80%99-opinion

Ortiz, Sabrina. “5 Ways ChatGPT Can Help You Write an Essay.” ZD Net.com. 19 Aug 2024. Web. 25 Oct 2024. https://www.zdnet.com/article/how-to-use-chatgpt-to-write-an-essay/

“Please write me a short poem about how amazing coffee is” prompt. ChatGPT, 2 Oct version, Open AI, 25 Oct 2024, chatgpt.com

“Please write me a short poem about how amazing coffee is” prompt. Gemini, 2.5 Flash version, Google, 25 Oct 2024, gemini.google.com/app

“What are examples of how chatbots can help with essays without helping a student cheat?” prompt. Gemini, 2.5 Flash version, Google, 25 Oct 2024, gemini.google.com/app

This essay is not from Writing Spaces. It is an original essay written for this Composition at CMU text to fill a topic gap, since none of the Writing Spaces essays in volumes 1–6 addressed chatbot usage.