How Can AI Help Developmental Editors?

Table of Contents

What Is AI Developmental Editing?

Why Use AI for Developmental Editing?

How Can You Use AI for Developmental Editing?

Step 1: Choose the Right Tool

Step 2: Get Pre-editing Support

Step 3: Fact-Check and Brainstorm During Editing

Step 4: Drafting Feedback

What Are the Challenges of Using AI for Developmental Editors?

Final Thoughts

Developmental editing is a complex task requiring creativity, strategy, people skills, and a deep understanding of publishing and genre. It’s no wonder we developmental editors tend to think highly of ourselves. When the topic of Artificial Intelligence (AI) first entered our personal narratives, it made sense that many of us assumed the technology would not be capable of assisting with this demanding, cerebral higher level of editing.

As AI has become entrenched in writing and lower levels of editing, developmental editors now may be starting to squirm and may be asking: Can a machine truly understand the nuances of a story? Will a bot render my hard-earned expertise into a bunch of algorithms? Is there still a place for me—the human—in this new technological era?

It’s true that AI’s analytical capabilities are well suited to helping developmental editors with many job duties. This article lays out how to use AI for developmental editing in a way that complements your human skills and allows you to improve your editing efficiency without compromising your editorial judgment or integrity—which should never be replaced. When a developmental editor uses AI to quickly identify a manuscript’s flaws, it frees up time to focus on creative solutions, resulting in higher-quality edits completed faster. Sounds too good to be true? It isn’t. Read on.

What Is AI Developmental Editing?

Developmental editing is a type of editing that focuses on improving the “big picture” elements of a manuscript. It analyzes fundamentals like structure, pacing, plot and character development, and theme and synthesizes the information into suggestions for improvement. This guides the author to create a manuscript that is cohesive and engaging and potentially loved one day by readers and critics alike.

AI developmental editing includes the same pieces as traditional developmental editing but adds AI tools to assist human editors with analysis, brainstorming, and reducing the manual workload. In AI developmental editing, tasks are divided, with the AI doing the tasks it can do best and the human editor doing the tasks they can do best.

Why Use AI for Developmental Editing?

Imagine doing your job but doing it faster and easier. Now imagine doing your job faster, easier, and better. Incorporating AI into your editorial workflow opens the doors to big gains in efficiency and quality, when used effectively.

• Speed: You can get back all of the hours you would have spent on your first read-through by having AI do it for you. Thanks to recent technological improvements, some AI tools can analyze entire book-length manuscripts in one go. Within seconds, they can spit out a chapter-by-chapter summary and report of the main weaknesses you would have identified yourself during your first pass. Now you’ll be more prepared when you start page one.

• Quality: AI can be excellent at identifying content gaps, recognizing inconsistencies, and brainstorming ideas and solutions. Working together with it means fewer subtle issues slip through the cracks and you will have options to consider that you may not have thought of on your own. (Think of it like a colleague you can bounce ideas off of.)

Now that you know the key benefits, let’s examine how to incorporate AI in your work.

How Can You Use AI for Developmental Editing?

There’s a place for AI at all stages of the developmental editing workflow, from pre-editing tasks to drafting feedback for authors. Here’s an overview of some ways to use AI in your work.

Step 1: Choose the Right AI Tool

The first step is to choose the best AI tool in the toolbox. This depends on the type of content you are working with.

Shorter Works

If you work on a chapter-by-chapter basis or you’re editing a shorter piece, such as an article or marketing copy, you have more options. Just about any chatbot (such as ChatGPT or Copilot) can handle your developmental editing analyses.

Longer Works

If you work with full-length book manuscripts, until recently, you had to break the document into smaller chunks the AI could take in. Now, there are tools that can do full-length manuscript analysis. One option is Claude, which is a favorite among book editors. The one I’m currently finding to be most accurate and consistent with long documents is Google’s NotebookLM. It also cites which exact page it pulled information from, making it easy to verify its work. Google Gemini also works incredibly well with long documents. (The main difference between NotebookLM and Gemini is the interface.)

Upgrade Your Editing Skills

Step 2: Get Pre-editing Support

Use AI to supercharge your prep work so your time spent editing inside the manuscript can be more focused.

Summaries and Synopses

Prompt the AI to generate a detailed synopsis or chapter-by-chapter summaries so you can quickly get an overview of the material.

Example Prompt: Please provide a synopsis of this book. Include all main points and key concepts.

https://video.wixstatic.com/video/6ea486_fdf9778f68494d7baea22dc03bcdcb17/1080p/mp4/file.mp4

Claude summarizing a 149-page public-domain philosophical work

Supplementary Documents

Developmental Editing involves tracking many different elements, page by page, as you go. The right AI tool can do this tracking for you and create documents both you and the author may find helpful, such as:

• Character Lists

• Setting Lists

• Plot Timelines

• Subtopic Lists

• Glossaries

Example Prompt: Please extract a list of settings in the book. Include a brief description of each setting.

https://video.wixstatic.com/video/6ea486_2894be93a426446188beb500fae3ce49/1080p/mp4/file.mp4

Gemini extracting the lengthy list of settings from an obscure public-domain fantasy book

Analyses to Identify Issues

Think of the problem areas authors tend to struggle with and ask the AI to analyze them. You can receive structured analyses while leaving room for your creative editorial influence and decision-making. Here are examples:

Plot Analysis

If you know the plot’s intended framework, prompt the AI to fit plot points onto the template to see where the plot may be misaligned.

Example Prompt: Please map the plot onto the Freytag’s pyramid story structure.

Follow-Up Prompt: Explain how well the plot follows the Freytag’s pyramid story structure.

https://video.wixstatic.com/video/6ea486_7761c3c949b34e10bbf5565524d4c398/1080p/mp4/file.mp4

NotebookLM organizing the fantasy book's plot according to the Freytag's Pyramid story structure

Character Analysis

Get help determining the overall strengths and weaknesses of specific characters, whether they make quality heroes or villains, whether they’re relatable, and more.

Example Prompt: Explain the strengths and weaknesses of the main character's arc and offer suggestions for improvement.

Content Gap Analysis

When working with nonfiction, you can prompt the AI to look for areas where adding subtopics could make the work feel more complete.

Example Prompt: Please review chapter 3 and list subtopics the author could add or expand to make the book more comprehensive.

https://video.wixstatic.com/video/6ea486_3a6f8b48bf96411e8704d7db30316d64/1080p/mp4/file.mp4

NotebookLM conducting a content gap analysis on the philosophy book

Structural Analysis

This analysis type works with both fiction and nonfiction. Use AI to probe whether the structure fits the expectations of the genre and makes sense.

Example Prompt: Please analyze the book's structure and list any places where the sequence of arguments lack logical flow.

Step 3: Fact-Check and Brainstorm During Editing

Wish you could get a quick second opinion or access your own personal fact-checker while editing? Now you’ve got one.

Fact-Checking

If you question whether you're correctly remembering the detail that seemed unimportant when you read it days ago, you can ask NotebookLM about it. It will review the copy of the manuscript you’ve uploaded and answer.

Example Prompt: Where did Zorak and Zena have the discussion about the magical ring?

Brainstorming

As you edit and come across an element that could be improved, you can ask AI to brainstorm a list of ideas to fix the issue. They won’t all be good, but there will likely be some you had not considered. You can use your experience and editorial judgment to select the best option.

Example Prompt: Please suggest plot events that could take place between chapters 9 and 10 to fill in any gaps in the timeline.

Try AI Editing

Step 4: Drafting Feedback

Through the analyses the AI conducted at the pre-editing stage, you’ll have pages of helpful insights you could put your touch on and incorporate into your editorial feedback. If there are any topics you may need to use careful wording with, such as suggesting the author cut a beloved character or favorite chapter, you could ask the AI for guidance with explaining your reasoning. You’ll want to be mindful not to have it sound like a robot wrote it, but it can quickly get you 80% of the way to the wording you want.

Example Prompt: Please write a compliment sandwich about why the Zorak character should be cut. The first paragraph should focus on a strength of the Zorak character. The second paragraph should explain why Zorak should be cut. The third paragraph should focus on a positive of the Zorak character while maintaining the recommendation to cut.

What Are the Challenges of Using AI for Developmental Editors?

While AI offers developmental editors many benefits, it also has limitations and should not be used without careful human oversight. One common drawback is AI tends to offer ideas that are generic (overused tropes), cliché (end every chapter on a cliffhanger), or simply misaligned with the author’s style (suggesting against experimentation in literary fiction).

Also, since AI isn’t human, it doesn’t know what it’s like to be human. You do. You can better gauge the manuscript’s emotional resonance than any program can. Your human editorial judgment, emotional intelligence, and experience remain integral to the developmental editing process.

Final Thoughts

When used well, AI tools like Claude and NotebookLM can be powerful partners to developmental editors. AI can join its analytical skills with your creativity and empathy to conduct edits that are efficient, comprehensive, creative, and that enable authors to create stronger connections with readers, tell better stories, and make their words have greater impact.

Learn with Erin

Erin Servais teaches editors to upskill with Artificial Intelligence through her AI for Editors courses and customized group training. She is known worldwide as a thought leader in AI education for editors, writers, and other publishing professionals. Learn more at www.aiforeditors.com and www.servaissolutions.com.

This article first appeared in the Independent Book Publishers Association's newsletter.

AI Use Disclosure: The author used AI to assist with creating the outline for this article.

AI Editing: Separating Facts from Fiction

As AI grows in popularity, it's normal to worry about how it will affect what we do as editors. But here's the thing: a lot of these concerns are based on misunderstandings about what AI can and can't do and how AI fits into the editing process. In this article, we’ll tackle these misconceptions so you’ll have a better understanding of how AI tools work and see how they can combine with essential human skills to help us be even better editors.

Misconception 1: AI Is Not Safe to Use with Clients’ Text

There are ways to use AI tools that provide data security. You need to know the specific settings for your tool of choice, however, because each is different. For instance, in ChatGPT, there is a setting you can switch on that stops the company from storing any text you put in their system long-term and using it to train new versions. Claude automatically does not use text to train new versions.

Whichever tool you use, it’s important to have your client’s or employer’s permission before you use AI with their text. Have a conversation with them to explain how you’ll use AI and the security measures you'll take to protect their work. It’s also wise to include a clause in your contract that makes it clear you’ll use this technology.

Misconception 2: AI Can’t Be Trusted

For many editors, getting the facts right is part of our jobs. It’s understandable we’d be worried about earlier AI models’ “hallucinations,” the term for when AI generates incorrect information. But there has been much improvement over the last several months that should alleviate this concern.

There are several quality AI-powered research tools available now. My favorite for general use is Perplexity. This works similarly to a search engine. You type in your query, but instead of getting pages of links of varying degrees of usefulness and reliability, you receive an answer akin to a personalized encyclopedia entry along with citations and links to sources that are overwhelmingly top-tier outlets like research journals, encyclopedias, and trusted news organizations. ChatGPT and Gemini also have access to the live web and can cite their sources when instructed to do so. This speeds up research and fact-checking immensely and ups the trust factor with AI tools because you can see exactly where they are getting their information.

Misconception 3: Using AI Is Cheating

AI can handle a lot of tasks on editors’ to-do lists and vastly speed up the process. When the work is suddenly so much easier, of course it can feel like using AI is cheating. Think about this: Was using spellcheck cheating? Or what about the dictionary? Was it cheating when you had to thumb through the pages to find the entry because you did not have every word in the English language memorized? Was it cheating when editors moved from marking up paper to using word processors?

Editing has always been a collaborative process between editors’ own knowledge, experience, and skills and the tools they've used—style guides, reference books, and technology. AI can be seen as another tool in the editors’ toolkit. When you use AI, it’s giving you suggestions, but you are still the one making the decisions of which suggestions to accept. You are still in control, using your knowledge of what is best for the writer and the reader.

Misconception 4: AI Is Not a Good Editor

Right now, AI tools like ChatGPT and Claude absolutely can conduct copyedits (straightforward checks for grammar, spelling, punctuation, and style) as well as humans can. I’ll admit that ChatGPT and Claude are often more accurate at copyediting than I am—and way faster, completing in seconds an edit that would take me hours.

I’ve found the editors who say AI isn't very skilled aren’t using the tools correctly. For example, they’ll use a vague prompt like “edit this” and then claim victory when it doesn’t make the precise changes they want. AI does what you tell it to do, not what you want it to do. If you want it to make a precise type of change, instruct it to do so.

AI is also quite good with content editing. It excels with idea generation. When you instruct it to examine a particular aspect of the text and offer suggestions for improvement, it can come back with so many ideas, some novel ones you may have never thought of on your own. You won’t want to pass along every idea it comes up with to the author, but it can certainly give you good ideas and help to spark ideas of your own.

Misconception 5: AI Can Replace Human Editors

I have heard multiple horror stories about entire editorial teams being laid off and replaced with...wait for it...Grammarly. Instead of writers sending their work to editors, writers are told to send their own work through Grammarly. And we all know how trustworthy Grammarly is, right? (I’m cringing. I encourage the use of many AI tools, but Grammarly is not among them.) Clearly these decisions are being made by people far removed from the day-to-day editorial process, and they are being made with shareholders and bonuses in mind, not readers. Because AI cannot and should not replace human editors.

These algorithms can catch mechanical errors, suggest improvements in grammar and syntax, and improve readability. However, AI can struggle to grasp the nuances of language, such as irony, sarcasm, or subtle shifts in tone. Since AI is built to follow formulas, it also struggles with allowing the creative freedom authors employ when purposefully bending or breaking language “rules.” And it cannot fully appreciate the cultural, historical, or personal backgrounds that shape a writer's voice and message.

Editing isn't just fixing spelling and pushing commas around. Editing involves a lot of soft skills. Editors build relationships with authors. We provide personalized guidance, and we make judgment calls based on our experience, what we know about the author, and what we know about helping the author do their best work for the reader. Human editors offer encouragement and education and nurture talent. Grammarly is not going to grow legs, hop out of the computer, and sit down with the author and explain to them, in precisely the way they know works best for that individual person, how they can improve.

Some companies care more about budgets than creating quality writing, however. This means if editors are to surf this technological wave successfully, they need to learn how to use AI tools so they can do their jobs faster and better than before—AI augmented, with their humanity intact.

Let's be real: AI is here, and it's only going to become a bigger part of our editing lives. By understanding what AI can and can't do, we can learn to use it as another powerful tool in our editing toolkit. It can help us with the nitty-gritty mechanics of editing, speed up our research and fact-checking, and even spark new ideas for improving a piece of writing. But AI can't replace the human touch we bring—our ability to connect with authors, understand the nuances of language, and make judgment calls based on our experience and expertise. With AI assisting us, we have more time to focus on what we do best: helping writers write well.

Erin Servais helps editors upskill through AI. Her AI for Editors course is known worldwide as the leading training for editors of all types, including medical editors, finance editors, education editors, corporate communications editors, and book editors.

A version of this article first appeared in the Editorial Freelancers Association's newsletter. Erin collaborated with artificial intelligence to write this article.

Email Erin: Erin@aiforeditors.com