Unreliable Narrator Designer
Engineers an unreliable narrator with consistent blind spots and clues that let attentive readers see the truth.
Prompt
ROLE: You are a literary craft mentor specializing in unreliable narration and reader manipulation. CONTEXT: My narrator is [NARRATOR], whose unreliability stems from [SOURCE: self-deception/limited knowledge/deliberate deception/mental state]. The truth the reader should eventually grasp: [HIDDEN TRUTH]. Story premise: [PREMISE]. TASK: 1. Define the narrator's specific BLIND SPOT and the psychological reason for it, so their distortions are consistent rather than random. 2. Establish the 'reliability contract': what the narrator reports accurately (to keep trust) versus where they distort. 3. Plant three CLUES — small contradictions, others' reactions, or telling omissions — that let an attentive reader sense the truth before the reveal. 4. Write a sample opening passage in the narrator's voice that establishes both charm and the first subtle crack. 5. Describe how the reveal should recontextualize earlier scenes (the 'rereadability' payoff). OUTPUT FORMAT: - UNRELIABILITY PROFILE - CLUE LEDGER (3 clues, each with placement guidance) - SAMPLE OPENING PASSAGE - REVEAL STRATEGY (short) CONSTRAINTS: The narrator must never feel like they're lying TO the reader arbitrarily — the distortion must be human and motivated. Clues should reward rereading without telegraphing the twist on first read.
How to use this prompt
- 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
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
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueForces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.
Learn this techniqueAsks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.
Learn this techniqueRecommended models
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
Three-Act Outline Architect
Builds a complete three-act outline with beat sheet, turning points, and midpoint reversal from a logline.
Sensory Scene Painter
Rewrites a flat scene into immersive prose using all five senses and grounded, character-filtered detail.
Character Voice Differentiator
Gives each character a distinct verbal fingerprint so dialogue is identifiable without speech tags.
Show-Don't-Tell Surgeon
Diagnoses telling passages and converts them to showing through action, dialogue, and subtext.