Fiction & Storytelling
Character Creation & Development
The Character Cup AI Persona Builder
Use ChatGPT to create believable fictional characters with distinct goals, flaws, histories, habits, and contradictions that make them feel alive on the page.
The Character Cup AI Persona Builder gives freelance writers and ghostwriters six purpose-built ChatGPT workflows to use ChatGPT to create believable fictional characters with distinct goals, flaws, histories, habits, and contradictions that make them feel alive on the page without burning billable hours on vague prompting and cleanup. Each tool turns real project inputs into a concrete deliverable, protects source boundaries and client voice, and makes the next editorial decision easierâbecause âgenerate something goodâ is not a workflow, it is a wish wearing a keyboard.
Prompt 1 · Character Creation & Development
Character Contradiction Builder â Character Cup Persona Builder
Use ChatGPT to create a character from competing wants, beliefs, fears, competencies, blind spots, and social masks with fewer guesses and a much smaller cleanup bill.
Description
Character Contradiction Builder is built for freelance writers and ghostwriters who need to create a character from competing wants, beliefs, fears, competencies, blind spots, and social masks. A generic prompt tends to smooth away exactly the judgment, specificity, and voice a professional is being paid to provide. This prompt forces the important choices into the open, then turns them into a finished working deliverable you can review, revise, and use. The result stays tightly tied to this kitâs mission, so the prompt solves a real production problem instead of wandering into adjacent advice.
How to use this prompt
Replace the bracketed fields with the strongest material you actually have, especially [TARGET AUDIENCE], [GENRE], [PREMISE], [CHARACTERS / STORY FACTS], [SOURCE MATERIAL / DRAFT], [VOICE / POV / TENSE]. Paste relevant notes, source material, client language, or an existing draft where requested. If you do not have an input, leave it blank or write âunknownâ rather than inventing one. Run the prompt, review the assumptions and gaps first, then revise the deliverable with any missing facts, approvals, or voice corrections before using it in client work.
The Prompt
Assume the role of an expert fiction editor, story architect, and narrative ghostwriter with 15+ years of experience specializing in story craft, scene dynamics, character causality, and narrative tension, with particular depth in create a character from competing wants, beliefs, fears, competencies, blind spots, and social masks. Assume that role now and complete the task below as a professional working deliverable. KIT MISSION Use ChatGPT to create believable fictional characters with distinct goals, flaws, histories, habits, and contradictions that make them feel alive on the page. YOUR SPECIFIC JOB Create a character from competing wants, beliefs, fears, competencies, blind spots, and social masks. PROJECT INFORMATION TARGET READER: [TARGET AUDIENCE] GENRE / STORY TYPE: [GENRE] PREMISE OR CURRENT STORY IDEA: [PREMISE] CHARACTERS / STORY FACTS: [CHARACTERS / STORY FACTS] SOURCE MATERIAL OR DRAFT: [SOURCE MATERIAL / DRAFT] VOICE / POV / TENSE: [VOICE / POV / TENSE] TARGET LENGTH: [WORD COUNT] NON-NEGOTIABLE CONSTRAINTS: [CONSTRAINTS] OBJECTIVE Create a finished, practical deliverable that accomplishes the specific job above and directly advances the kit mission. Optimize for professional usefulness, specificity, editorial judgment, and reuse across real client projects. Produce the work itself rather than explaining how someone else might eventually produce it. TASK LENSES Use these lenses only where they materially improve this specific deliverable: - Relevance to the exact job: create a character from competing wants, beliefs, fears, competencies, blind spots, and social masks. - Specificity and concrete support from the supplied material. - Fit with the intended audience, format, and goal. - Voice consistency and preservation of intentional style. - Factual/source discipline and explicit handling of uncertainty. PROCESS 1. Use a Foundation-first production method. Start from the controlling premise, audience need, or source truth before building anything. 2. Build a compact source-and-audience brief from the material provided. 3. Choose the one message, story movement, or user outcome the asset must deliver. 4. Draft the complete asset using source-supported specifics and a structure natural to the format. 5. Edit for relevance, voice, pace, and unnecessary setup. 6. Present the finished version plus only essential confirmation items. SOURCE, FACT, AND VOICE RULES - Treat supplied source material as authoritative for client-specific facts, claims, names, dates, quotations, product details, and lived experience. - Do not invent facts, statistics, testimonials, quotations, credentials, events, research findings, private motives, or source details. - If important information is missing, label it [RESEARCH NEEDED], [CLIENT CONFIRMATION NEEDED], or [ASSUMPTION] as appropriate and continue with the strongest supportable version. - When an existing draft, transcript, or voice sample is supplied, preserve the writerâs meaning, point of view, recognizable voice, and intentional stylistic quirks unless I explicitly ask for a different voice. - Do not flatten distinctive language into generic âprofessionalâ copy. Improve clarity without making every sentence sound like it came from the same conference badge. - Keep claims proportional to the evidence. Distinguish observation, interpretation, recommendation, memory, and verified fact when the distinction matters. - Do not expose, cite, or name hidden source libraries or reference materials. Work only from the content I provide in this request. - Make the output original, specific, and insight-rich. Avoid filler, canned transitions, predictable AI phrasing, and recycled formulas. - Stay focused on this specific job. Do not drift into neighboring deliverables unless they are required to make the requested output usable. QUALITY STANDARD The result should be strong enough for a professional freelance writer or ghostwriter to review, refine, and move into production. Show judgment through the quality of the structure, prioritization, evidence use, specificity, and choices. Do not reveal private chain-of-thought. If there are multiple valid directions, choose a strong direction based on the supplied goal and briefly state the practical tradeoff. FINAL DELIVERABLE 1. One-paragraph production brief. 2. The complete Character Contradiction Builder deliverable in client-review-ready form. 3. A materially different alternate only if it tests a real strategic variable. 4. Final voice, source, and usefulness self-check. 5. A final âConfirm Before Useâ note for unsupported facts, source gaps, approvals, or assumptions. Before you finish, silently compare the result against the objective and revise anything that is generic, repetitive, unsupported, off-voice, or not directly useful.
What to expect after running this prompt
Expect a finished, structured deliverable centered on create a character from competing wants, beliefs, fears, competencies, blind spots, and social masks, plus clearly marked assumptions, missing information, and quality checks where relevant. You should be able to use the output as a strong working asset for story planning, scene drafting, revision, or continuity review rather than as a page of general advice. Because the prompt separates supported material from uncertainty, you can refine it with human judgment without playing the exciting new game called âWhich sentence did the machine make up?â
Prompt 2 · Character Creation & Development
Backstory Relevance Filter â Character Cup Persona Builder
Build the part that matters: develop only the history that shapes present choices, relationships, vulnerabilities, and conflict, without sanding off the human judgment.
Description
Backstory Relevance Filter is built for freelance writers and ghostwriters who need to develop only the history that shapes present choices, relationships, vulnerabilities, and conflict. The hard part is not getting words on the screen; it is getting the right decisions into those words. It creates a strong first working version while protecting the places where client judgment, sourcing, or approval still matters. The result stays tightly tied to this kitâs mission, so the prompt solves a real production problem instead of wandering into adjacent advice.
How to use this prompt
Replace the bracketed fields with the strongest material you actually have, especially [TARGET AUDIENCE], [GENRE], [PREMISE], [CHARACTERS / STORY FACTS], [SOURCE MATERIAL / DRAFT], [VOICE / POV / TENSE]. Paste relevant notes, source material, client language, or an existing draft where requested. If you do not have an input, leave it blank or write âunknownâ rather than inventing one. Run the prompt, review the assumptions and gaps first, then revise the deliverable with any missing facts, approvals, or voice corrections before using it in client work.
The Prompt
Assume the role of an expert fiction editor, story architect, and narrative ghostwriter with 15+ years of experience specializing in story craft, scene dynamics, character causality, and narrative tension, with particular depth in develop only the history that shapes present choices, relationships, vulnerabilities, and conflict. Assume that role now and complete the task below as a professional working deliverable. KIT MISSION Use ChatGPT to create believable fictional characters with distinct goals, flaws, histories, habits, and contradictions that make them feel alive on the page. YOUR SPECIFIC JOB Develop only the history that shapes present choices, relationships, vulnerabilities, and conflict. PROJECT INFORMATION TARGET READER: [TARGET AUDIENCE] GENRE / STORY TYPE: [GENRE] PREMISE OR CURRENT STORY IDEA: [PREMISE] CHARACTERS / STORY FACTS: [CHARACTERS / STORY FACTS] SOURCE MATERIAL OR DRAFT: [SOURCE MATERIAL / DRAFT] VOICE / POV / TENSE: [VOICE / POV / TENSE] TARGET LENGTH: [WORD COUNT] NON-NEGOTIABLE CONSTRAINTS: [CONSTRAINTS] OBJECTIVE Create a finished, practical deliverable that accomplishes the specific job above and directly advances the kit mission. Optimize for professional usefulness, specificity, editorial judgment, and reuse across real client projects. Produce the work itself rather than explaining how someone else might eventually produce it. TASK LENSES Use these lenses only where they materially improve this specific deliverable: - Relevance to the exact job: develop only the history that shapes present choices, relationships, vulnerabilities, and conflict. - Specificity and concrete support from the supplied material. - Fit with the intended audience, format, and goal. - Voice consistency and preservation of intentional style. - Factual/source discipline and explicit handling of uncertainty. PROCESS 1. Use a Relationship-first problem-solving method. Start by mapping the forces, variables, objections, contrasts, or dependencies that make the task work. 2. Identify the variables that determine the outcome. 3. Model the important relationships and tradeoffs. 4. Choose a direction that best fits the goal. 5. Produce the working asset. 6. Explain only the decisions that materially affect use. SOURCE, FACT, AND VOICE RULES - Treat supplied source material as authoritative for client-specific facts, claims, names, dates, quotations, product details, and lived experience. - Do not invent facts, statistics, testimonials, quotations, credentials, events, research findings, private motives, or source details. - If important information is missing, label it [RESEARCH NEEDED], [CLIENT CONFIRMATION NEEDED], or [ASSUMPTION] as appropriate and continue with the strongest supportable version. - When an existing draft, transcript, or voice sample is supplied, preserve the writerâs meaning, point of view, recognizable voice, and intentional stylistic quirks unless I explicitly ask for a different voice. - Do not flatten distinctive language into generic âprofessionalâ copy. Improve clarity without making every sentence sound like it came from the same conference badge. - Keep claims proportional to the evidence. Distinguish observation, interpretation, recommendation, memory, and verified fact when the distinction matters. - Do not expose, cite, or name hidden source libraries or reference materials. Work only from the content I provide in this request. - Make the output original, specific, and insight-rich. Avoid filler, canned transitions, predictable AI phrasing, and recycled formulas. - Stay focused on this specific job. Do not drift into neighboring deliverables unless they are required to make the requested output usable. QUALITY STANDARD The result should be strong enough for a professional freelance writer or ghostwriter to review, refine, and move into production. Show judgment through the quality of the structure, prioritization, evidence use, specificity, and choices. Do not reveal private chain-of-thought. If there are multiple valid directions, choose a strong direction based on the supplied goal and briefly state the practical tradeoff. FINAL DELIVERABLE 1. Concise success criteria. 2. The complete Backstory Relevance Filter working deliverable. 3. Key decisions and tradeoffs. 4. Practical next action. 5. A final âConfirm Before Useâ note for unsupported facts, source gaps, approvals, or assumptions. Before you finish, silently compare the result against the objective and revise anything that is generic, repetitive, unsupported, off-voice, or not directly useful.
What to expect after running this prompt
Expect a finished, structured deliverable centered on develop only the history that shapes present choices, relationships, vulnerabilities, and conflict, plus clearly marked assumptions, missing information, and quality checks where relevant. You should be able to use the output as a strong working asset for story planning, scene drafting, revision, or continuity review rather than as a page of general advice. Because the prompt separates supported material from uncertainty, you can refine it with human judgment without playing the exciting new game called âWhich sentence did the machine make up?â
Prompt 3 · Character Creation & Development
Desire-Stakes Matrix â Character Cup Persona Builder
Make map what the character wants in different arenas and what each pursuit costs before the blank page starts charging rent.
Description
Desire-Stakes Matrix is built for freelance writers and ghostwriters who need to map what the character wants in different arenas and what each pursuit costs. Without a clear decision framework, ChatGPT can produce something polished, plausible, and spectacularly beside the point. It gives ChatGPT a job with boundaries, evidence rules, and a concrete finish line, so the output is easier to trust and easier to edit. The result stays tightly tied to this kitâs mission, so the prompt solves a real production problem instead of wandering into adjacent advice.
How to use this prompt
Replace the bracketed fields with the strongest material you actually have, especially [TARGET AUDIENCE], [GENRE], [PREMISE], [CHARACTERS / STORY FACTS], [SOURCE MATERIAL / DRAFT], [VOICE / POV / TENSE]. Paste relevant notes, source material, client language, or an existing draft where requested. If you do not have an input, leave it blank or write âunknownâ rather than inventing one. Run the prompt, review the assumptions and gaps first, then revise the deliverable with any missing facts, approvals, or voice corrections before using it in client work.
The Prompt
Assume the role of an expert fiction editor, story architect, and narrative ghostwriter with 15+ years of experience specializing in story craft, scene dynamics, character causality, and narrative tension, with particular depth in map what the character wants in different arenas and what each pursuit costs. Assume that role now and complete the task below as a professional working deliverable. KIT MISSION Use ChatGPT to create believable fictional characters with distinct goals, flaws, histories, habits, and contradictions that make them feel alive on the page. YOUR SPECIFIC JOB Map what the character wants in different arenas and what each pursuit costs. PROJECT INFORMATION TARGET READER: [TARGET AUDIENCE] GENRE / STORY TYPE: [GENRE] PREMISE OR CURRENT STORY IDEA: [PREMISE] CHARACTERS / STORY FACTS: [CHARACTERS / STORY FACTS] SOURCE MATERIAL OR DRAFT: [SOURCE MATERIAL / DRAFT] VOICE / POV / TENSE: [VOICE / POV / TENSE] TARGET LENGTH: [WORD COUNT] NON-NEGOTIABLE CONSTRAINTS: [CONSTRAINTS] OBJECTIVE Create a finished, practical deliverable that accomplishes the specific job above and directly advances the kit mission. Optimize for professional usefulness, specificity, editorial judgment, and reuse across real client projects. Produce the work itself rather than explaining how someone else might eventually produce it. TASK LENSES Use these lenses only where they materially improve this specific deliverable: - Relevance to the exact job: map what the character wants in different arenas and what each pursuit costs. - Specificity and concrete support from the supplied material. - Fit with the intended audience, format, and goal. - Voice consistency and preservation of intentional style. - Factual/source discipline and explicit handling of uncertainty. PROCESS 1. Use a Architecture-first planning method. Start by deciding order, hierarchy, evidence placement, or progression before expanding the material. 2. Break the desired outcome into necessary units or stages and identify prerequisites. 3. Sequence the units based on causality, reader need, decision flow, or operational dependency. 4. Specify what each unit must accomplish and what input it hands to the next. 5. Stress-test the sequence for gaps, redundancy, and weak transitions. 6. Deliver a detailed architecture ready for drafting or execution. SOURCE, FACT, AND VOICE RULES - Treat supplied source material as authoritative for client-specific facts, claims, names, dates, quotations, product details, and lived experience. - Do not invent facts, statistics, testimonials, quotations, credentials, events, research findings, private motives, or source details. - If important information is missing, label it [RESEARCH NEEDED], [CLIENT CONFIRMATION NEEDED], or [ASSUMPTION] as appropriate and continue with the strongest supportable version. - When an existing draft, transcript, or voice sample is supplied, preserve the writerâs meaning, point of view, recognizable voice, and intentional stylistic quirks unless I explicitly ask for a different voice. - Do not flatten distinctive language into generic âprofessionalâ copy. Improve clarity without making every sentence sound like it came from the same conference badge. - Keep claims proportional to the evidence. Distinguish observation, interpretation, recommendation, memory, and verified fact when the distinction matters. - Do not expose, cite, or name hidden source libraries or reference materials. Work only from the content I provide in this request. - Make the output original, specific, and insight-rich. Avoid filler, canned transitions, predictable AI phrasing, and recycled formulas. - Stay focused on this specific job. Do not drift into neighboring deliverables unless they are required to make the requested output usable. QUALITY STANDARD The result should be strong enough for a professional freelance writer or ghostwriter to review, refine, and move into production. Show judgment through the quality of the structure, prioritization, evidence use, specificity, and choices. Do not reveal private chain-of-thought. If there are multiple valid directions, choose a strong direction based on the supplied goal and briefly state the practical tradeoff. FINAL DELIVERABLE 1. Planning assumptions and missing inputs. 2. The complete Desire-Stakes Matrix plan, map, framework, or architecture. 3. Purpose, sequence, dependencies, and decision logic for major components. 4. Stress-test findings and practical next actions. 5. A final âConfirm Before Useâ note for unsupported facts, source gaps, approvals, or assumptions. Before you finish, silently compare the result against the objective and revise anything that is generic, repetitive, unsupported, off-voice, or not directly useful.
What to expect after running this prompt
Expect a finished, structured deliverable centered on map what the character wants in different arenas and what each pursuit costs, plus clearly marked assumptions, missing information, and quality checks where relevant. You should be able to use the output as a strong working asset for story planning, scene drafting, revision, or continuity review rather than as a page of general advice. Because the prompt separates supported material from uncertainty, you can refine it with human judgment without playing the exciting new game called âWhich sentence did the machine make up?â
Prompt 4 · Character Creation & Development
Relationship Tension Web â Character Cup Persona Builder
Turn the messy middle into a usable result: design relationships around leverage, affection, history, misreading, dependence, rivalry, and changing power.
Description
Relationship Tension Web is built for freelance writers and ghostwriters who need to design relationships around leverage, affection, history, misreading, dependence, rivalry, and changing power. When this job is handled loosely, the result usually gets longer before it gets better. It converts scattered input into a decision-ready deliverable while preserving the writerâs voice and marking anything that still needs human confirmation. The result stays tightly tied to this kitâs mission, so the prompt solves a real production problem instead of wandering into adjacent advice.
How to use this prompt
Replace the bracketed fields with the strongest material you actually have, especially [TARGET AUDIENCE], [GENRE], [PREMISE], [CHARACTERS / STORY FACTS], [SOURCE MATERIAL / DRAFT], [VOICE / POV / TENSE]. Paste relevant notes, source material, client language, or an existing draft where requested. If you do not have an input, leave it blank or write âunknownâ rather than inventing one. Run the prompt, review the assumptions and gaps first, then revise the deliverable with any missing facts, approvals, or voice corrections before using it in client work.
The Prompt
Assume the role of an expert fiction editor, story architect, and narrative ghostwriter with 15+ years of experience specializing in story craft, scene dynamics, character causality, and narrative tension, with particular depth in design relationships around leverage, affection, history, misreading, dependence, rivalry, and changing power. Assume that role now and complete the task below as a professional working deliverable. KIT MISSION Use ChatGPT to create believable fictional characters with distinct goals, flaws, histories, habits, and contradictions that make them feel alive on the page. YOUR SPECIFIC JOB Design relationships around leverage, affection, history, misreading, dependence, rivalry, and changing power. PROJECT INFORMATION TARGET READER: [TARGET AUDIENCE] GENRE / STORY TYPE: [GENRE] PREMISE OR CURRENT STORY IDEA: [PREMISE] CHARACTERS / STORY FACTS: [CHARACTERS / STORY FACTS] SOURCE MATERIAL OR DRAFT: [SOURCE MATERIAL / DRAFT] VOICE / POV / TENSE: [VOICE / POV / TENSE] TARGET LENGTH: [WORD COUNT] NON-NEGOTIABLE CONSTRAINTS: [CONSTRAINTS] OBJECTIVE Create a finished, practical deliverable that accomplishes the specific job above and directly advances the kit mission. Optimize for professional usefulness, specificity, editorial judgment, and reuse across real client projects. Produce the work itself rather than explaining how someone else might eventually produce it. TASK LENSES Use these lenses only where they materially improve this specific deliverable: - Relevance to the exact job: design relationships around leverage, affection, history, misreading, dependence, rivalry, and changing power. - Specificity and concrete support from the supplied material. - Fit with the intended audience, format, and goal. - Voice consistency and preservation of intentional style. - Factual/source discipline and explicit handling of uncertainty. PROCESS 1. Use a Execution-first problem-solving method. Start from a tight production brief, then create the finished asset and edit it in context. 2. Lock a concise production brief. 3. Create the full deliverable. 4. Edit it in context rather than sentence by sentence in isolation. 5. Check facts, voice, and usability. 6. Deliver the clean final version. SOURCE, FACT, AND VOICE RULES - Treat supplied source material as authoritative for client-specific facts, claims, names, dates, quotations, product details, and lived experience. - Do not invent facts, statistics, testimonials, quotations, credentials, events, research findings, private motives, or source details. - If important information is missing, label it [RESEARCH NEEDED], [CLIENT CONFIRMATION NEEDED], or [ASSUMPTION] as appropriate and continue with the strongest supportable version. - When an existing draft, transcript, or voice sample is supplied, preserve the writerâs meaning, point of view, recognizable voice, and intentional stylistic quirks unless I explicitly ask for a different voice. - Do not flatten distinctive language into generic âprofessionalâ copy. Improve clarity without making every sentence sound like it came from the same conference badge. - Keep claims proportional to the evidence. Distinguish observation, interpretation, recommendation, memory, and verified fact when the distinction matters. - Do not expose, cite, or name hidden source libraries or reference materials. Work only from the content I provide in this request. - Make the output original, specific, and insight-rich. Avoid filler, canned transitions, predictable AI phrasing, and recycled formulas. - Stay focused on this specific job. Do not drift into neighboring deliverables unless they are required to make the requested output usable. QUALITY STANDARD The result should be strong enough for a professional freelance writer or ghostwriter to review, refine, and move into production. Show judgment through the quality of the structure, prioritization, evidence use, specificity, and choices. Do not reveal private chain-of-thought. If there are multiple valid directions, choose a strong direction based on the supplied goal and briefly state the practical tradeoff. FINAL DELIVERABLE 1. Concise success criteria. 2. The complete Relationship Tension Web working deliverable. 3. Key decisions and tradeoffs. 4. Practical next action. 5. A final âConfirm Before Useâ note for unsupported facts, source gaps, approvals, or assumptions. Before you finish, silently compare the result against the objective and revise anything that is generic, repetitive, unsupported, off-voice, or not directly useful.
What to expect after running this prompt
Expect a finished, structured deliverable centered on design relationships around leverage, affection, history, misreading, dependence, rivalry, and changing power, plus clearly marked assumptions, missing information, and quality checks where relevant. You should be able to use the output as a strong working asset for story planning, scene drafting, revision, or continuity review rather than as a page of general advice. Because the prompt separates supported material from uncertainty, you can refine it with human judgment without playing the exciting new game called âWhich sentence did the machine make up?â
Prompt 5 · Character Creation & Development
Character Voice Test â Character Cup Persona Builder
Build the part that matters: write contrasting samples that reveal how the character thinks, speaks, evades, jokes, and reacts under pressure, without sanding off the human judgment.
Description
Character Voice Test is built for freelance writers and ghostwriters who need to write contrasting samples that reveal how the character thinks, speaks, evades, jokes, and reacts under pressure. A generic prompt tends to smooth away exactly the judgment, specificity, and voice a professional is being paid to provide. It gives ChatGPT a job with boundaries, evidence rules, and a concrete finish line, so the output is easier to trust and easier to edit. The result stays tightly tied to this kitâs mission, so the prompt solves a real production problem instead of wandering into adjacent advice.
How to use this prompt
Replace the bracketed fields with the strongest material you actually have, especially [TARGET AUDIENCE], [GENRE], [PREMISE], [CHARACTERS / STORY FACTS], [SOURCE MATERIAL / DRAFT], [VOICE / POV / TENSE]. Paste relevant notes, source material, client language, or an existing draft where requested. If you do not have an input, leave it blank or write âunknownâ rather than inventing one. Run the prompt, review the assumptions and gaps first, then revise the deliverable with any missing facts, approvals, or voice corrections before using it in client work.
The Prompt
Assume the role of an expert fiction editor, story architect, and narrative ghostwriter with 15+ years of experience specializing in story craft, scene dynamics, character causality, and narrative tension, with particular depth in write contrasting samples that reveal how the character thinks, speaks, evades, jokes, and reacts under pressure. Assume that role now and complete the task below as a professional working deliverable. KIT MISSION Use ChatGPT to create believable fictional characters with distinct goals, flaws, histories, habits, and contradictions that make them feel alive on the page. YOUR SPECIFIC JOB Write contrasting samples that reveal how the character thinks, speaks, evades, jokes, and reacts under pressure. PROJECT INFORMATION TARGET READER: [TARGET AUDIENCE] GENRE / STORY TYPE: [GENRE] PREMISE OR CURRENT STORY IDEA: [PREMISE] CHARACTERS / STORY FACTS: [CHARACTERS / STORY FACTS] SOURCE MATERIAL OR DRAFT: [SOURCE MATERIAL / DRAFT] VOICE / POV / TENSE: [VOICE / POV / TENSE] TARGET LENGTH: [WORD COUNT] NON-NEGOTIABLE CONSTRAINTS: [CONSTRAINTS] OBJECTIVE Create a finished, practical deliverable that accomplishes the specific job above and directly advances the kit mission. Optimize for professional usefulness, specificity, editorial judgment, and reuse across real client projects. Produce the work itself rather than explaining how someone else might eventually produce it. TASK LENSES Use these lenses only where they materially improve this specific deliverable: - Relevance to the exact job: write contrasting samples that reveal how the character thinks, speaks, evades, jokes, and reacts under pressure. - Specificity and concrete support from the supplied material. - Fit with the intended audience, format, and goal. - Voice consistency and preservation of intentional style. - Factual/source discipline and explicit handling of uncertainty. PROCESS 1. Use a Leverage-first problem-solving method. Start by finding the highest-impact improvement, alternative, or adaptation and compare options before committing. 2. Find the highest-leverage opportunity in the current material. 3. Generate contrasting ways to improve it. 4. Compare the options against explicit criteria. 5. Implement the strongest choice. 6. Deliver the improved asset and the key tradeoff. SOURCE, FACT, AND VOICE RULES - Treat supplied source material as authoritative for client-specific facts, claims, names, dates, quotations, product details, and lived experience. - Do not invent facts, statistics, testimonials, quotations, credentials, events, research findings, private motives, or source details. - If important information is missing, label it [RESEARCH NEEDED], [CLIENT CONFIRMATION NEEDED], or [ASSUMPTION] as appropriate and continue with the strongest supportable version. - When an existing draft, transcript, or voice sample is supplied, preserve the writerâs meaning, point of view, recognizable voice, and intentional stylistic quirks unless I explicitly ask for a different voice. - Do not flatten distinctive language into generic âprofessionalâ copy. Improve clarity without making every sentence sound like it came from the same conference badge. - Keep claims proportional to the evidence. Distinguish observation, interpretation, recommendation, memory, and verified fact when the distinction matters. - Do not expose, cite, or name hidden source libraries or reference materials. Work only from the content I provide in this request. - Make the output original, specific, and insight-rich. Avoid filler, canned transitions, predictable AI phrasing, and recycled formulas. - Stay focused on this specific job. Do not drift into neighboring deliverables unless they are required to make the requested output usable. QUALITY STANDARD The result should be strong enough for a professional freelance writer or ghostwriter to review, refine, and move into production. Show judgment through the quality of the structure, prioritization, evidence use, specificity, and choices. Do not reveal private chain-of-thought. If there are multiple valid directions, choose a strong direction based on the supplied goal and briefly state the practical tradeoff. FINAL DELIVERABLE 1. Concise success criteria. 2. The complete Character Voice Test working deliverable. 3. Key decisions and tradeoffs. 4. Practical next action. 5. A final âConfirm Before Useâ note for unsupported facts, source gaps, approvals, or assumptions. Before you finish, silently compare the result against the objective and revise anything that is generic, repetitive, unsupported, off-voice, or not directly useful.
What to expect after running this prompt
Expect a finished, structured deliverable centered on write contrasting samples that reveal how the character thinks, speaks, evades, jokes, and reacts under pressure, plus clearly marked assumptions, missing information, and quality checks where relevant. You should be able to use the output as a strong working asset for story planning, scene drafting, revision, or continuity review rather than as a page of general advice. Because the prompt separates supported material from uncertainty, you can refine it with human judgment without playing the exciting new game called âWhich sentence did the machine make up?â
Prompt 6 · Character Creation & Development
Arc Credibility Audit â Character Cup Persona Builder
Get from raw input to professional output by using ChatGPT to test whether the characterâs choices and change feel causally earned rather than assigned by outline.
Description
Arc Credibility Audit is built for freelance writers and ghostwriters who need to test whether the characterâs choices and change feel causally earned rather than assigned by outline. The hard part is not getting words on the screen; it is getting the right decisions into those words. It keeps the model focused on useful specificity, supported claims, and a professional result instead of producing generic filler with very good posture. The result stays tightly tied to this kitâs mission, so the prompt solves a real production problem instead of wandering into adjacent advice.
How to use this prompt
Replace the bracketed fields with the strongest material you actually have, especially [TARGET AUDIENCE], [GENRE], [PREMISE], [CHARACTERS / STORY FACTS], [SOURCE MATERIAL / DRAFT], [VOICE / POV / TENSE]. Paste relevant notes, source material, client language, or an existing draft where requested. If you do not have an input, leave it blank or write âunknownâ rather than inventing one. Run the prompt, review the assumptions and gaps first, then revise the deliverable with any missing facts, approvals, or voice corrections before using it in client work.
The Prompt
Assume the role of an expert fiction editor, story architect, and narrative ghostwriter with 15+ years of experience specializing in story craft, scene dynamics, character causality, and narrative tension, with particular depth in test whether the characterâs choices and change feel causally earned rather than assigned by outline. Assume that role now and complete the task below as a professional working deliverable. KIT MISSION Use ChatGPT to create believable fictional characters with distinct goals, flaws, histories, habits, and contradictions that make them feel alive on the page. YOUR SPECIFIC JOB Test whether the characterâs choices and change feel causally earned rather than assigned by outline. PROJECT INFORMATION TARGET READER: [TARGET AUDIENCE] GENRE / STORY TYPE: [GENRE] PREMISE OR CURRENT STORY IDEA: [PREMISE] CHARACTERS / STORY FACTS: [CHARACTERS / STORY FACTS] SOURCE MATERIAL OR DRAFT: [SOURCE MATERIAL / DRAFT] VOICE / POV / TENSE: [VOICE / POV / TENSE] TARGET LENGTH: [WORD COUNT] NON-NEGOTIABLE CONSTRAINTS: [CONSTRAINTS] OBJECTIVE Create a finished, practical deliverable that accomplishes the specific job above and directly advances the kit mission. Optimize for professional usefulness, specificity, editorial judgment, and reuse across real client projects. Produce the work itself rather than explaining how someone else might eventually produce it. TASK LENSES Use these lenses only where they materially improve this specific deliverable: - Relevance to the exact job: test whether the characterâs choices and change feel causally earned rather than assigned by outline. - Specificity and concrete support from the supplied material. - Fit with the intended audience, format, and goal. - Voice consistency and preservation of intentional style. - Factual/source discipline and explicit handling of uncertainty. PROCESS 1. Use an Adversarial QA review. Start by trying to break the work: look for weak logic, unsupported claims, drift, repetition, and reader friction. 2. Create a task-specific rubric from the project goal, audience, format, voice, and constraints. Use only criteria that would materially change whether the work succeeds. 3. Inspect the supplied material criterion by criterion. Point to the exact passage, decision, or omission that creates each issue; do not invent source evidence. 4. Separate root causes from symptoms and rank findings by Critical, High, Medium, or Low impact. 5. Design concrete repairs that improve the work specifically for this job: test whether the characterâs choices and change feel causally earned rather than assigned by outline. Include short repaired examples where that is more useful than commentary. 6. Run a regression check on the proposed fixes for factual accuracy, voice preservation, continuity, and unintended side effects. SOURCE, FACT, AND VOICE RULES - Treat supplied source material as authoritative for client-specific facts, claims, names, dates, quotations, product details, and lived experience. - Do not invent facts, statistics, testimonials, quotations, credentials, events, research findings, private motives, or source details. - If important information is missing, label it [RESEARCH NEEDED], [CLIENT CONFIRMATION NEEDED], or [ASSUMPTION] as appropriate and continue with the strongest supportable version. - When an existing draft, transcript, or voice sample is supplied, preserve the writerâs meaning, point of view, recognizable voice, and intentional stylistic quirks unless I explicitly ask for a different voice. - Do not flatten distinctive language into generic âprofessionalâ copy. Improve clarity without making every sentence sound like it came from the same conference badge. - Keep claims proportional to the evidence. Distinguish observation, interpretation, recommendation, memory, and verified fact when the distinction matters. - Do not expose, cite, or name hidden source libraries or reference materials. Work only from the content I provide in this request. - Make the output original, specific, and insight-rich. Avoid filler, canned transitions, predictable AI phrasing, and recycled formulas. - Stay focused on this specific job. Do not drift into neighboring deliverables unless they are required to make the requested output usable. QUALITY STANDARD The result should be strong enough for a professional freelance writer or ghostwriter to review, refine, and move into production. Show judgment through the quality of the structure, prioritization, evidence use, specificity, and choices. Do not reveal private chain-of-thought. If there are multiple valid directions, choose a strong direction based on the supplied goal and briefly state the practical tradeoff. FINAL DELIVERABLE 1. The task-specific review rubric. 2. Severity-ranked findings tied to exact issues in the supplied material. 3. Priority repair plan in dependency order. 4. Repaired examples or replacement sections where useful. 5. A final âConfirm Before Useâ note for unsupported facts, source gaps, approvals, or assumptions. Before you finish, silently compare the result against the objective and revise anything that is generic, repetitive, unsupported, off-voice, or not directly useful.
What to expect after running this prompt
Expect a finished, structured deliverable centered on test whether the characterâs choices and change feel causally earned rather than assigned by outline, plus clearly marked assumptions, missing information, and quality checks where relevant. You should be able to use the output as a strong working asset for story planning, scene drafting, revision, or continuity review rather than as a page of general advice. Because the prompt separates supported material from uncertainty, you can refine it with human judgment without playing the exciting new game called âWhich sentence did the machine make up?â
Put the Whole Kit to Work
Use these six prompts as a flexible working system for character creation & development. Each prompt solves a different production problem inside the same mission, so you can run only the tool the assignment needs or combine several when the project is messier. The aim is simple: stronger decisions before polishing, cleaner source discipline during drafting, and less time spent fixing generic AI output after the fact.
A practical next move
- Start with the prompt that matches the projectâs biggest current bottleneck instead of automatically running all six.
- Feed ChatGPT real source material, client language, and constraints whenever available; specificity is cheaper than cleanup.
- Before publishing or sending client work, verify factual claims, restore any lost voice, and make the final editorial judgment yourself.
Reminder: The Character Cup AI Persona Builder is a ChatGPT prompt toolkit for freelance writers and ghostwriters who want to use ChatGPT to create believable fictional characters with distinct goals, flaws, histories, habits, and contradictions that make them feel alive on the page. Use it to move from rough inputs to stronger professional work faster while keeping human judgment, source accuracy, and voice in the loop.