Create a style guide for AI writing.
Teach AI what makes writing sound right to you. It will study your work and writing you admire, describe the style, and try it out before producing a reusable guide.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Study writing you supply or permit it to find, along with your preferences and influences.
- Describe the style, check current research on overused AI writing when search is available, and test the guide through a sample you review.
What to have ready
- Writing samples, links, pasted passages, or descriptions of what you like and dislike; start with what you have.
- Examples of writing you admire are welcome. Connected searches of your writing require your permission.
Where you come in
- Choose which sources the AI may read and correct its proposed style description.
- Review and refine the sample until it sounds right to you; choose a download format if you want one.
What you'll get
A reusable style guide with your approved sample and instructions for making it available in your AI setup, plus a download if supported.
You're done when
You have a reusable style guide, a sample that sounds right to you, and a clear way to make the guide available in the AI you use.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. Help me create a style guide that an LLM can use to write in the style I prefer. Ask one question at a time when you need my input, and wait for answers that affect the next step. ### 1. Agree on access to your writing You may inspect which connections and setup options are available before asking for consent, but do not retrieve my writing through those connections until I have granted permission for this activity. Ask specifically for permission to read my sent emails and reports, memos, or other work I have written, unless I have already granted it, and wait for my answer. Respect the sources and scope I permit. Use writing I have supplied for this activity within that permission, without treating it as blanket permission to search elsewhere. Once permitted, find examples yourself through the allowed connections. If useful access is unavailable, investigate available setup and permitted export or upload options before asking me to provide replacement material. Explain what could enable access and how it would improve the guide. Ask for the specific user action or permission needed when necessary, and offer to walk me through an export or upload. Welcome files, links, pasted passages, or descriptions through a route I permit. If I decline connected access, work with the material and preferences I choose to share. Continue with usable supplied material while explaining any limits. ### 2. Understand preferences and describe the style Ask me to point out writing I am particularly pleased with or dislike. Invite examples of writing I admire: a colleague's work, a favorite author, or instructions such as “tight but casual” or “never use second person.” Explain that more material can make the guide better, while working with what I have. Distinguish my own writing from influences and my preferences from habits I may want to change. Study what makes this writing distinctive: voice, rhythm, structure, specificity, humor, evidence, and relationship with the reader. Describe the proposed style in one short paragraph, followed by a concise list of its key elements. Ground these in examples. Ask for corrections and wait. ### 3. Check overused AI-writing patterns - Search current primary research and recent first-hand editorial observations for overused AI-writing words and patterns. - Distinguish measured tendencies from editorial preferences and cite the dated sources briefly. - Use that research to add practical avoidance instructions and better alternatives. - Include no em dashes and no figurative “load bearing”; watch for stock language such as “delve,” “seamless,” and “underscore.” Treat these as editing preferences, not tests of who wrote something. - Keep dated research sources separate from the reusable guide. - If web search is unavailable, say so and use the stated preferences without claiming fresh research. ### 4. Revise the sample until you approve it Apply my corrections and write a short sample on a subject supported by the material. Ask whether it sounds right and wait for my response. Revise the sample and guide from my feedback, and repeat the sample review as needed until I approve it. Do not treat a sample you generated as approved before I say it sounds right. ### 5. Deliver the guide and explain how to reuse it - Produce the complete, self-contained style guide for future LLMs, including the style paragraph, actionable rules, avoidance guidance, and approved sample. - Ask which AI app or agent environment I use if you cannot tell. - Check its actual capabilities and current instructions, then explain the simplest supported way to make the guide available there. - Offer a downloadable version in my preferred format and create it if supported. These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
View full AI instructions
Create a style guide for AI writing.
What the AI will do
- Study writing you supply or permit it to find, along with your preferences and influences.
- Describe the style, check current research on overused AI writing when search is available, and test the guide through a sample you review.
What you can provide
- Writing samples, links, pasted passages, or descriptions of what you like and dislike; start with what you have.
- Examples of writing you admire are welcome. Connected searches of your writing require your permission.
Where you'll take part
- Choose which sources the AI may read and correct its proposed style description.
- Review and refine the sample until it sounds right to you; choose a download format if you want one.
What you'll get
A reusable style guide with your approved sample and instructions for making it available in your AI setup, plus a download if supported.
Activity context
Teach AI what makes writing sound right to you. It will study your work and writing you admire, describe the style, and try it out before producing a reusable guide.
For the user
Paste this prompt into your work AI. It will ask permission before searching your writing and invite you to point out favorites, disappointments, and influences. More material gives it a better basis for the guide; start with whatever you have. You will correct its style description and react to the sample: what sounds like you, what feels off, and what you want more of. It will revise the guide and sample until the sample sounds right to you, explain how to reuse the guide in your setup, and offer a download in your preferred format.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Help me create a style guide that an LLM can use to write in the style I prefer. Ask one question at a time when you need my input, and wait for answers that affect the next step.
1. Agree on access to your writing
You may inspect which connections and setup options are available before asking for consent, but do not retrieve my writing through those connections until I have granted permission for this activity. Ask specifically for permission to read my sent emails and reports, memos, or other work I have written, unless I have already granted it, and wait for my answer. Respect the sources and scope I permit.
Use writing I have supplied for this activity within that permission, without treating it as blanket permission to search elsewhere.
Once permitted, find examples yourself through the allowed connections. If useful access is unavailable, investigate available setup and permitted export or upload options before asking me to provide replacement material. Explain what could enable access and how it would improve the guide. Ask for the specific user action or permission needed when necessary, and offer to walk me through an export or upload. Welcome files, links, pasted passages, or descriptions through a route I permit.
If I decline connected access, work with the material and preferences I choose to share. Continue with usable supplied material while explaining any limits.
2. Understand preferences and describe the style
Ask me to point out writing I am particularly pleased with or dislike. Invite examples of writing I admire: a colleague's work, a favorite author, or instructions such as “tight but casual” or “never use second person.” Explain that more material can make the guide better, while working with what I have. Distinguish my own writing from influences and my preferences from habits I may want to change.
Study what makes this writing distinctive: voice, rhythm, structure, specificity, humor, evidence, and relationship with the reader. Describe the proposed style in one short paragraph, followed by a concise list of its key elements. Ground these in examples. Ask for corrections and wait.
3. Check overused AI-writing patterns
- Search current primary research and recent first-hand editorial observations for overused AI-writing words and patterns.
- Distinguish measured tendencies from editorial preferences and cite the dated sources briefly.
- Use that research to add practical avoidance instructions and better alternatives.
- Include no em dashes and no figurative “load bearing”; watch for stock language such as “delve,” “seamless,” and “underscore.” Treat these as editing preferences, not tests of who wrote something.
- Keep dated research sources separate from the reusable guide.
- If web search is unavailable, say so and use the stated preferences without claiming fresh research.
4. Revise the sample until you approve it
Apply my corrections and write a short sample on a subject supported by the material. Ask whether it sounds right and wait for my response. Revise the sample and guide from my feedback, and repeat the sample review as needed until I approve it. Do not treat a sample you generated as approved before I say it sounds right.
5. Deliver the guide and explain how to reuse it
- Produce the complete, self-contained style guide for future LLMs, including the style paragraph, actionable rules, avoidance guidance, and approved sample.
- Ask which AI app or agent environment I use if you cannot tell.
- Check its actual capabilities and current instructions, then explain the simplest supported way to make the guide available there.
- Offer a downloadable version in my preferred format and create it if supported.
Done when
You have a reusable style guide, a sample that sounds right to you, and a clear way to make the guide available in the AI you use.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.