AI Is a Writing Assistant, Not a Writer: How to Use It Right

I have published more than a hundred books and ghostwritten over fifty for other people, and I use AI most days I work. That sentence gets me in trouble in both directions. Half the writing world thinks admitting it makes me a fraud. The other half thinks it means I am about to tell you the machine can write your book. Neither is right, and the space between those two reactions is where the honest answer lives.

The honest answer starts with a better picture of what the thing is. AI is not a writer. It is not a coauthor. It is a digital assistant, and the moment you treat it like an assistant you hired, everything about how to use it well falls into place.

What does it mean to treat AI like an assistant?

Think about how you would work with a person you brought on to help you write. You would learn fast where they are strong and where they are weak. Maybe they are a sharp researcher who pulls together background in an afternoon that would take you two days. Maybe they are good at rough structure and hopeless at a finished sentence. You would not fire them for the things they cannot do. You would stop handing them those things.

That is exactly the relationship. You direct the assistant. You say, go research the history of this topic and give me the major turning points. You say, I am stuck on how to open this chapter, show me three ways in so I can react to them. You say, I have a mess of notes, help me build an outline I can argue with. You say, my brain has quit for the day and I cannot find the next paragraph, give me a bad draft I can fix. Every one of those is a real assistant doing real assistant work. None of them is the assistant writing your book.

You are still the brain. You still do the writing. The judgment about what belongs, what is true, what sounds like you, what earns its place on the page, all of that stays with you, because it is the part the assistant cannot do and never will. This is the same line I draw in whether AI can write your book, and the answer there is the same as the answer here. It can help you write your book. It cannot write it.

Where does AI break?

The reservations are not small print. They are the reason you keep the assistant on a short leash, and every one of them has cost a writer somewhere real money and real embarrassment.

It hallucinates. It will hand you a fact that is wrong and a citation that does not exist, delivered with the same calm confidence it uses for the things it gets right. I have watched it invent a source, invent a study, invent a quote, and never once flag that it was making it up, because it does not know it is making it up. If you put its facts into your book without checking every one, you are signing your name to whatever it invented. I go deeper into this in why bad inputs break AI projects, but the short version is that the machine is a confident liar and you are the fact checker.

It drifts. Give it a long enough job and it slowly forgets what you told it at the start, wandering away from your instructions a little at a time until the thing it is producing no longer matches the thing you asked for. I wrote a whole piece on AI drift because it is the failure people notice last and pay for most.

It flattens your voice. Hand it your writing and ask it to help, and it will quietly sand you down toward the average of everything it has ever read. Your odd rhythms, your specific word choices, the small things that make a sentence sound like you and not like anyone else, it planes them off without asking. What comes back is smoother and deader.

And it makes everything the same. This is the one that surprises people. Ask AI to help with a nonfiction book and you get chapters that all open the same way, close the same way, run the same length, and sit at the same flat middle level of quality. Ask it to help with fiction and you get the same thing, every chapter the same size and the same wishy-washy shape. The spine of the book comes out uniform, and uniform is another word for mediocre. A real book has chapters that breathe differently because the material demands it. The machine does not know the material demands anything.

Why does AI struggle with hard or dark writing?

There is a whole category of writing the assistant simply will not do well, and it is the category that matters most in a lot of books. Anything confrontational. Anything dark. It cannot write a sex scene worth reading, and it will not write most violent scenes at all. You can push it, and it will grudgingly produce something, the way you can push a nervous employee into a task they hate, but what you get back is watered down and wrong, and you spend more time fixing it than you would have spent writing it clean.

This is where the whack-a-mole starts. If you lean on AI for the material it is bad at, you end up with a manuscript that reads wrong in ways you cannot immediately name. A scene that should land hard lands soft. A moment of real conflict comes out weirdly polite. You keep poking at it, fixing one dead spot only to find another, never quite understanding why the whole thing feels off. The answer is that you asked the assistant to do the work it was never going to be able to do, and the fix is not more prompting. The fix is to write those parts yourself.

What about the ethics of using AI to write?

This is the hard one, and I am not going to pretend it is settled, because it is not, and it is not going to be. The AI models learned from other people’s work. David Baldacci sat in front of a Senate subcommittee in July 2025 and described watching his son ask ChatGPT to write a plot in the style of a David Baldacci novel. In about five seconds it produced three pages carrying plot lines, character names, and narrative pulled from across his books. He said it felt like someone had backed a truck up to his imagination and stolen everything he had ever created. That is a real objection from a serious writer, and it deserves a straight answer instead of a dodge.

Here is my straight answer. It is out there. You can use it or not use it, and taking a noble stand against it does not change a single thing about whether it exists or what it can do. Say you are writing a kids’ book and you ask AI for an outline, and it hands you something that reads a lot like an R.L. Stine Goosebumps book. You could also walk into a library, pull a Stine off the shelf, and follow that outline yourself. Writers have studied and borrowed structure from other writers for as long as there have been books. The machine did it faster and from a bigger pile, and that is a genuine problem, but it is a problem baked into the tool, not a switch you can flip by disapproving of it.

So if you choose to write with AI, you take the caveats that come with it. One of them is that somebody may notice, and somebody may write you a scathing review for it. Fair enough. But somebody was going to write you a scathing review anyway. No matter what you write or how you write it, someone out there will hate it and say so at length. That is the job. It is not a reason to avoid a useful tool, and it is not a reason to pretend the tool is cleaner than it is.

Are writing tools like ProWritingAid and Grammarly any better?

The dedicated writing apps are a different category from the big chat models, and one of them earns a spot in my toolkit. ProWritingAid is a good tool. It does a solid job proofreading and a solid job on spelling, and I think it is better than Grammarly at both. Its overused-word finder is genuinely useful, because once you can see your own crutch words you can fix them going forward. I use it and I recommend it, with one honest caveat: the AI-suggestion side of it is a work in progress, the same as the AI portion of everything else right now. Lean on the proofreading and spelling, treat the AI rewrite suggestions the way you treat any AI, as something to check instead of accepting on faith, and it does right by you.

Hemingway is an even lighter option, and it does its narrow job well because it stays in its lane as a proofreader and readability checker that does not try to rewrite you. Between a tool like ProWritingAid for the careful proofread and Hemingway for a quick readability pass, you have what you need for the mechanics. What you should not do is hand any of them a loose rein over your finished prose. When you use AI for a grammar pass, tell it plainly: do not change a word except the ones I point at. Give it free rein on your manuscript and it will go off rewriting the whole thing while your back is turned, flattening you the way it always does.

So how should a writer use AI?

Point it at the assistant work and keep it off the writing. Let it research. Let it rough out an outline you will tear apart. Let it break a block by handing you something bad enough to argue with. Let it check your grammar under strict orders. Let it help you find phrases for a title or back-cover copy, which is marketing, not the book. And keep it far away from your voice, your facts before you have checked them, your hard scenes, and any decision about what the book is.

The writers who get burned are the ones who forgot they hired an assistant and started treating it like the author. The writers who do well are the ones who stayed the brain, kept the machine on the tasks it is good at, and did the writing themselves. If you want the fuller map of where the tool helps and where it hurts, I laid it out in what AI is good at and the six places it will break your work. And if you would rather hand the whole thing to a human who uses these tools the careful way and takes responsibility for every word, that is the ghostwriting work I do. Either way, the rule is the same. It is a tool. Use it wisely, and it earns its keep. Use it as a shortcut around the work, and it will show.

Frequently Asked Questions