Role-Playing Prompts: A Guide for Editors
Updated: Oct 13
An AI prompting technique you’ll want to try is role-playing. With role-playing, you instruct AI to take on a persona, such as an editor or reader.
The role-playing approach adapts the AI’s responses and gives you more actionable insights and ideas for edits. Plus, it’s a prompting method you can use whether you’re a copyeditor, developmental editor, line editor, or author coach. Intrigued? Let’s dive in!
AI Role-Playing Prompts: A Guide for Editors: Key Takeaways
Role-playing prompts sharpen AI output for more targeted feedback.
The formula is simple: assign a role, then give a direction.
Always get written permission before putting other people’s work into an AI tool.
First Things First
Before we get to the fun stuff, let’s talk about something that matters more than any prompt: your writers’ proprietary work.
When you upload a manuscript into any AI tool, you’re handing their unpublished work to an unseen and unknown third party. This was always hazardous, and it’s become a bigger deal in the last couple of years as the publishing world engages more deeply with AI.
Here are a few ground rules around AI consent and disclosure:
How to Use AI With Client Documents
Get Permission First. Don’t put any part of a client’s manuscript into an AI tool without their express and written permission. This is a confidentiality issue that publishing contracts are beginning to address directly.
Mind Your AI Settings. Check whether the AI tool trains its models on your prompts, attachments, and responses. There should be a privacy setting where you can opt out of training the AI model. Some paid plans, particularly enterprise plans, will opt out by default. Even if you have opted out of training, AI platforms keep logs of chat threads for 30 days to 5 years or more. It’s wise to remove identifying details from anything you upload to AI and omit them from your prompt.
Be Transparent. Share your AI use policy with the writers you work with to clarify how AI is used in your work. Offer them a way to opt out, too. AI use disclosure is the norm now, and being upfront about your AI use builds trust.
Don’t let this scare you off. Just handle consent and confidentiality up front, and you’ve covered your bases for the techniques below.
What Is Prompting?
Before we delve into the role-playing method, let’s revisit the basics of prompting with AI. A prompt is an instruction you give to AI to get it to generate a specific response.
For instance, you might use a direct prompt, such as “Summarize the following text,” followed by a few lengthy paragraphs you want AI to review. AI would then offer a concise overview, transforming your bulky text into an easily digestible snippet.
What Is Role-Playing Prompting?
Role-playing prompting is taking the art of question-asking one step further. You’re not just requesting information; you’re setting a scene and having AI adopt a role.
Why Is Role-Playing Effective?
Contextual Clarity = Focused Feedback: Role-playing prompts steer the AI toward context that generic and broad prompts don’t have. AI understands the scenario better and can respond with more specific, targeted output. You’re narrowing the AI’s field of view to suit your needs.
Enhanced Creativity: Stepping into different roles stimulates creativity for you and your AI and encourages you both to think about a problem from multiple perspectives.
Role-Playing Prompt Format
The formula for a role-playing prompt is super simple and can be broken down into two main pieces:
[Role] + [Task]
Role: This is where you tell AI what persona to take on. This sets the stage and lets the AI know what characteristics it should adopt and expertise it should convey.
Task: After you’ve set the role, you’ll want to specify a job suited to that role.
Role-Playing Prompt Format Examples
You are a [role]. Do this [task].
Pretend you’re a [role]. Provide your top advice on [topic].
Act like you’re a [role]. Explain how you would handle [situation].
Role-play as a [role]. Assess the following [text].
Role-Playing as Editor and Reader
Editors may find it most helpful to instruct AI to take on the personas of “editor” and “reader.” Here are starting ideas for using each role. AI results vary, so you will likely get answers from AI that are different from these. Try it out and see!
Role-Playing as the Editor
If you’re dealing with a text that needs better organization, clarity, consistency, or technical refinement, the editor role is your best bet.
Examples of Role-Playing as the Editor
Prompt: You are an experienced line editor of children’s books. How would you improve this for middle-grade readers? Amelia was extremely apprehensive as she cautiously made her way through the dark and foreboding forest, wondering if perhaps she had made an error in judgment by embarking on this particular journey alone.
AI’s Answer: I would (1) choose concrete words over abstract ones; (2) remove hedging and commit to the emotion; (3) have the character be engaged with sensation rather than think it; (4) shorten the sentences. Amelia's heart pounded. The forest was darker than she remembered — and quieter, too. Maybe coming here alone hadn't been such a great idea.
Prompt: You are an experienced content editor of think-tank reports. Read through the attached white paper and assess whether the argument is well-supported.
AI’s Answer: The argument is promising but not yet well-supported. Key gaps: (1) It treats a correlation as causal, without ruling out confounds like wealth or timing. (2) The data window is narrow and results could look different over a longer span. (3) It doesn't seriously engage the strongest case for Program A. (4) The recommendation — a full funding shift — is bigger than the evidence supports, which points more to "worth further study."
Role-Playing as the Reader
If you want to understand how a text might be received by its intended audience, use a reader persona. You’ll get insights into the text’s readability and engagement factors, helping you make reasoned editorial decisions.
Examples of Role-Playing as the Reader
Prompt: You are a company employee. Is this annual report effective at conveying the difficulties the company is facing and creating a tone where people feel they can contribute to a turnaround success?
AI’s Answer: (1) Passive voice for bad news reads as spin, not honesty. (2) Numbers without explanation erodes trust or reads as denial. (3) Vague calls to contribute doesn't give people a real foothold. Instead try (1) Ownership — "we expanded too fast" builds more trust. (2) Ask employees for specific contributions.
Prompt: You are a legislator interested in educational policy. Are you able to take away action items from the attached report?
AI’s Answer: (1) The report needs specifics like funding for attendance officers, requiring early-warning tracking systems, or mandating family outreach programs. (2) The report needs cost estimates; recommendations without fiscal scope stall at committee. (3) There is no timeline or owner; unclear whether implementation falls to districts, the state board, or requires new statute. (4) It is unclear which subgroups or districts are hit hardest, so it's hard to know where a first intervention would have the most impact.
The role-playing method with AI is like having a Swiss Army knife for editing. But as always, take AI’s responses as suggestions, not authoritative answers.
It’s versatile, it’s fun, and it can make your work so much better. The next time you’re stuck on a tricky paragraph and are looking for answers or inspiration, remember—you have roles to play!
***
AI tools evolve quickly—their features, pricing, and data policies can change without much fanfare. The specifics in this article were accurate at publication. Before making decisions based on any tool mentioned here, check its website directly.
Erin Servais is the founder of the AI for Editors courses, the first AI training program built specifically for editorial professionals. Since launching it in August 2023, she has trained editors and content professionals from more than 20 countries, including people from Big Five publishers, Ivy League universities, US government and United Nations agencies, and major tech companies. She has presented on AI in content development for the Book Industry Study Group, the University of Chicago, the UNC Chapel Hill School of Journalism and Media, and the ConVEx conference, and she has written about AI and editing for the Editorial Freelancers Association and the Independent Book Publishers Association. Her work has been featured in Jane Friedman’s The Bottom Line and Mignon Fogarty’s AI Sidequest. A professional editor for more than 20 years, Erin is a former ACES board member and has taught copyediting at UC San Diego Extended Studies.
Have questions? Email Erin → Erin@aiforeditors.com
