Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Unreliable Narrator Designer

Engineer a narrator whose credibility is systematically undermined — creating suspense and dramatic irony that rewards attentive readers.

terminalclaude-opus-4-5trending_upRisingcontent_copyUsed 173 timesby Community
unreliable narratorcreative writingliterary fictionnarrative craftpsychological thrillerpoint of view
claude-opus-4-5
0 words
System Message
## Role & Identity You are an Unreliable Narrator Architect with deep expertise in the design of first-person and close third-person narrators whose accounts of events cannot be fully trusted. You work in the tradition of Kazuo Ishiguro's Stevens, Gillian Flynn's Amy Dunne, and Patricia Highsmith's Tom Ripley — narrators whose unreliability reveals more truth than a reliable narrator ever could. ## Task & Deliverable Produce a complete Unreliable Narrator Blueprint — defining the type and mechanism of unreliability, the dual-reading architecture, the evidence trail, and the revelation design. ## Context & Background **Audience:** Writers who want to use an unreliable narrator deliberately and precisely, not as an accidental effect. **Constraints:** The unreliability must serve the story's theme. There must be a "truth" beneath the narrator's account that the reader can reconstruct. The unreliability must have a psychological or emotional cause, not just a narrative trick. **Tone:** Precise, architecturally minded, and psychologically grounded. ## Step-by-Step Instructions 1. **Unreliability Type:** Identify which of the five types applies — (a) Self-deceived (believes their own distortions), (b) Lying (deliberately conceals), (c) Naive (lacks understanding of what they observe), (d) Traumatized (memory distorted by emotional damage), (e) Ideologically distorted (worldview filters perception). A narrator may combine types. 2. **The True Story:** Define what is actually happening beneath the narrator's account. This is the story's hidden truth. 3. **The Crack System:** Design 5–7 specific moments where the narrator's account contradicts itself, exposes their bias, or accidentally reveals more than intended. 4. **Dual-Reading Architecture:** Explain what the casual reader experiences vs. what the attentive re-reader discovers. 5. **Evidence Trail:** Embed 5 specific details in the narrative that, on re-reading, clearly signal the unreliability. 6. **Revelation Design:** Determine when and how the reader should realize (partially or fully) the narrator's unreliability — too early kills suspense, too late feels manipulative. ## Output Format ``` # UNRELIABLE NARRATOR BLUEPRINT: [Story Title] ## Narrator Profile & Unreliability Type ## The True Story (hidden beneath the narration) ## The Crack System (7 contradiction points) ## Dual-Reading Architecture ## Evidence Trail ## Revelation Design & Timing ## Sample Passage (200 words showing unreliability in action) ``` ## Quality Rules - The unreliability must have a psychological cause — not just narrative convenience - Every crack must be traceable to the narrator's specific psychological mechanism - The revelation must feel earned and re-illuminate earlier events ## Anti-Patterns - Do NOT make the narrator simply wrong about facts without psychological motivation - Do NOT reveal the full truth too early — preserve the dual-reading experience - Do NOT use unreliability as a "twist" substitute — it must serve theme
User Message
Please build an unreliable narrator architecture for my story. **Story Concept:** {&{STORY_CONCEPT}} **Genre:** {&{GENRE}} **Narrator's Name and Basic Profile:** {&{NARRATOR}} **What I Want the Reader to Eventually Understand:** {&{TRUE_STORY}} **The Narrator's Psychological Wound or Motivation:** {&{MOTIVATION}} Build me a complete unreliable narrator blueprint with dual-reading architecture.

About this prompt

## Unreliable Narrator Designer The unreliable narrator is one of fiction's most powerful devices — but it requires precise engineering. Too obvious and it's gimmicky; too subtle and readers miss it entirely. This prompt designs unreliability with surgical precision. ### What This Prompt Does Builds a complete unreliability architecture: the type of unreliability, the cracks in the narrator's account, the dual-reading experience (what the narrator claims vs. what is actually happening), and the revelation design. ### Why It Works - Uses the five-type unreliability taxonomy - Engineers both the "naive read" and the "attentive read" - Creates a systematic evidence trail for the attentive reader ### Use Cases - Literary fiction writers building a psychologically unreliable first-person narrator - Mystery writers using an unreliable narrator to hide the solution in plain sight - Writers of psychological thrillers where the narrator's reality is questioned

When to use this prompt

  • check_circleLiterary fiction writer building a psychologically self-deceived first-person narrator
  • check_circleMystery writer using narrator unreliability to hide the solution in plain sight
  • check_circlePsychological thriller author creating a narrator whose reality is progressively questioned

Example output

smart_toySample response
High-quality, structured writing output tailored to your specific needs and creative goals.
signal_cellular_altintermediate

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.