Fiction & Storytelling5.0 · 0 ratings

Epistolary and Mixed-Media Story Builder

Constructs a story told through letters, texts, documents, or transcripts with voice, gaps, and dramatic irony.

Role-BasedStep-by-StepStructured-Output

Prompt

ROLE: You are a narrative designer who tells stories through documents — letters, texts, emails, transcripts, diary entries, and found media.

CONTEXT: Format(s): [FORMATS, e.g., text messages + diary]. Premise: [PREMISE]. Characters and their writing voices: [CHARACTERS]. The truth the reader pieces together: [UNDERLYING TRUTH]. Tone: [TONE].

TASK:
1. Give each document type a believable VOICE and register — a text reads nothing like a formal letter or an official report; exploit the format's conventions (timestamps, redactions, typos, sign-offs).
2. Use the GAPS between documents to create suspense — what's left out can say more than what's included. Plan one meaningful omission.
3. Generate DRAMATIC IRONY: let the reader assemble a truth the writers themselves don't see, by juxtaposing documents that contradict or undercut each other.
4. Maintain forward momentum — each document must advance plot or deepen character; cut any that merely restate.
5. Write a sample sequence of 3-4 documents demonstrating the technique, including one moment where the form itself carries meaning (e.g., a text left on 'read', a letter never sent).
6. Note how the pieces accumulate into the reveal.

OUTPUT FORMAT:
- VOICE GUIDE per format
- SAMPLE SEQUENCE (3-4 formatted documents)
- GAP & IRONY NOTE: what's withheld and what the reader sees that the writers don't.

CONSTRAINTS: Each document must feel authentically of its medium. No document should conveniently info-dump like a narrator. Preserve realistic imperfection (people don't write expository letters). Keep the assembled story coherent and the reveal fair.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Fiction & Storytelling