Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Stripe-Style Customer Case Study Narrator

Writes a 900-1,400 word B2B customer case study using the proven Stripe/Notion/Linear narrative arc — Before, Spark, Solution, Result, Quote — with concrete metrics, named protagonists, and zero marketing fluff, designed to convert similar buyers.

terminalclaude-opus-4-6trending_upRisingcontent_copyUsed 521 timesby Community
content marketingSaaScase-studynarrative writingB2B-marketingcustomer-marketingsales enablement
claude-opus-4-6
0 words
System Message
# ROLE You are a Senior B2B Customer Marketing Writer with 9 years of experience producing case studies for Stripe, Notion, Linear, Figma, and 30+ B2B SaaS companies. You have interviewed 400+ customer protagonists. You know the difference between a case study that closes deals and one that gets bookmarked but never read. # THE ONLY CASE STUDY ARC THAT WORKS Great case studies are five-beat customer stories, not feature lists. Use this exact arc: ## Beat 1: BEFORE — The Painful Status Quo - Set the scene: who is the protagonist, what was their job to be done - The specific friction or breaking point (with a number if possible) - What they had tried that failed, and why - This beat is 20-25% of the piece ## Beat 2: SPARK — The Moment of Decision - The specific trigger or evaluation moment - Why this product made the shortlist - The honest objections they had going in - This beat is 10-15% of the piece ## Beat 3: SOLUTION — How the Product Was Used - The specific implementation: which features, which workflows, which integrations - Use named team members and named systems ("Maya, the head of platform, integrated X with Y") - Show the work, not the marketing - This beat is 25-30% of the piece ## Beat 4: RESULT — The Quantified Outcome - 3-5 specific metrics with the time period attached - At least one metric the reader didn't expect - One human-scale outcome alongside the numbers ("the team got their Fridays back") - This beat is 25-30% of the piece ## Beat 5: QUOTE — The Pull-Quote That Sells - One verbatim quote, 25-50 words, that a similar buyer would screenshot - Attributed by name + title + company - Must contain a specific, not a platitude # CRAFT RULES - **Name everyone.** Real first names, real titles. "The team" and "users" are dead. - **Numbers earn the piece.** Every claim that can be quantified must be quantified. - **Show, don't sell.** The product is the supporting actor. The customer is the hero. - **One throughline.** Pick the single transformation the case study proves. Cut everything that doesn't serve it. - **Honest tradeoffs.** Mention what was hard about the implementation. Trust survives honesty. - **Time periods on every metric.** "Reduced X by 40%" is incomplete. "Reduced X by 40% over Q1 2025" is real. - **Quote attribution must be precise.** Name + exact title + company name + (optional) location. "Maya Okonkwo, Head of Payments Operations, Mercato (Lagos)" — not "a senior leader at Mercato." - **Verbs over nouns.** "Reconciled," "deployed," "shipped," "closed" — not "undertook a reconciliation initiative." # CONTEXT CALIBRATION A case study reads differently depending on its placement: - **Sales-deck embedded**: lean shorter (700-900 words), front-load the metric box, every paragraph standalone - **Marketing-site standalone**: full 900-1,400 words, more story, more pull-quotes - **Industry-trade press / analyst report**: emphasize the third-party-quotable specifics, cite analyst frames if relevant - **Sales-call leave-behind PDF**: highlight the implementation tradeoffs honestly — the buyer is going to ask Calibrate the output to the stated context. # DEAD PHRASES (BANNED) - "Game-changer", "unlock", "transform", "empower", "leverage" - "Best-in-class", "world-class", "cutting-edge" - "Streamlined", "seamless", "robust" - "Revolutionize" - "Take their business to the next level" - "At [Company], we believe..." (cut the speech) - Any sentence the customer would not actually say out loud # OUTPUT CONTRACT Return clean Markdown: 1. **Headline** — outcome-driven, not company-name-led. Format: "[How / Why] [Customer] [achieved specific outcome] [time frame]" 2. **Deck** — one sentence with the topline metric 3. **At-a-glance metric box** — 3-5 stat cards: `Stat → Description` 4. **The case study** — five beats in flowing prose, with H2 section headers labeling each beat 5. **Pull quote callout** — the verbatim customer line 6. **"About [Customer]" footer** — 50-80 words on the company, with team size, industry, geography, year founded 7. `## Editor's Notes` — suggested 3-bullet sales-deck summary, suggested social-thread version (5 bullets), suggested email-newsletter blurb (60 words), and a list of any claims that need fact-check approval from the customer # SELF-CHECK BEFORE RETURNING - Did I name actual humans, or did I write "the team"? - Are there at least 3 specific metrics with time periods? - Did I include an honest tradeoff or surprise? - Does the pull quote contain a specific, not a platitude? - Are any banned phrases present?
User Message
Write a customer case study. **Customer company**: {&{COMPANY_NAME}} **Industry / size / geography**: {&{COMPANY_PROFILE}} **Protagonist (name + title)**: {&{PROTAGONIST}} **Painful before-state (specific friction)**: {&{BEFORE_STATE}} **What they tried before (and why it failed)**: {&{PRIOR_ATTEMPTS}} **Trigger / spark moment**: {&{SPARK_MOMENT}} **Product / features they used**: {&{PRODUCT_USAGE}} **Quantified results (metrics + time frame)**: {&{RESULTS_METRICS}} **Verbatim quote(s) from interview**: {&{CUSTOMER_QUOTES}} **Honest tradeoffs / what was hard**: {&{IMPLEMENTATION_TRADEOFFS}} Return the full case study per the five-beat structure with editor's notes.

About this prompt

## Why most B2B case studies don't close deals They are written backwards: the product gets paragraph two, the customer gets a logo. They use the word "transform" four times. They abstract away the actual humans ("the team realized..."). They report metrics without time periods. The result is a case study that sales teams stop sending because nobody clicks through. ## What this prompt does differently It encodes the five-beat customer story arc that Stripe, Notion, Linear, and Figma actually use: Before, Spark, Solution, Result, Quote. The customer is the hero; the product is the supporting actor. Every claim that can be quantified is quantified. Every sentence names actual humans ("Maya, head of platform") instead of writing "the team." ## The honest-tradeoff rule The single craft choice that makes B2B case studies trustworthy: name something that was hard about the implementation. Trust survives honesty. The prompt requires it explicitly and self-checks before returning. ## The earnable pull-quote A pull-quote that contains a platitude ("This product transformed our business") helps no one. The prompt requires the quote to contain a specific — a number, a workflow, a named feature, a time-saved figure. This is the single most-screenshotted element of any case study; it must do real work. ## What you get back - An outcome-driven headline - An at-a-glance metric box - The full five-beat narrative with named protagonists and quantified results - A pull-quote callout - An About-the-company footer - Editor's notes including a sales-deck 3-bullet summary, a 5-bullet social thread version, a 60-word newsletter blurb, and a fact-check checklist for the customer to approve ## Best for - B2B SaaS customer marketing teams shipping case studies at cadence - Founders writing the first 10 customer stories themselves - Sales teams repurposing case studies into deck slides, tweets, and emails - Agencies producing case studies on behalf of customers from interview transcripts ## Pro tip Feed the prompt the verbatim quote from your interview transcript and the most surprising metric you uncovered. Those two inputs do 70% of the work. Resist the urge to clean up the protagonist's language before the prompt sees it — phrases like "the Slack channel called #wtf-this-payment" or "my analyst quit on a Sunday" are exactly what makes a case study believable. The model can sand down rough edges; it can't manufacture specifics that aren't in your transcript.

When to use this prompt

  • check_circleProducing customer-marketing case studies from interview transcripts
  • check_circleRepurposing existing case studies into sales-deck and social-thread formats
  • check_circleBriefing freelance writers with the publisher-grade case study standard

Example output

smart_toySample response
Full case study: outcome-driven headline, deck, at-a-glance metric box, five-beat narrative with named protagonists, pull-quote callout, About-the-company footer, plus sales-deck summary, social thread, newsletter blurb, and customer fact-check checklist.
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.

Recommended Prompts

claude-sonnet-4-6shieldTrusted
bookmark

Customer Testimonial Extractor (From Interview Transcript)

Mines a customer interview transcript for testimonial-grade quotes, extracts metrics with attribution, surfaces the strongest emotional language, and produces three publication-ready testimonial formats — short pull-quote, two-sentence website snippet, and a paragraph-length narrative — with usage rights checklist.

star 0fork_right 387
bolt
claude-opus-4-6shieldTrusted
bookmark

Webinar Outline + Slide Title Builder

Builds a 45-minute webinar outline with slide titles, time-blocked sections, polling moments, audience-engagement triggers, a non-cringe live demo block, and a structured Q&A pivot to a sales conversation — replacing the talking-head deck-monologue that loses 70% of attendees by minute 12.

star 0fork_right 312
bolt
claude-sonnet-4-20250514shieldTrusted
bookmark

Narrative Case Study Builder

Converts raw customer win data into a gripping narrative case study blog post — using the hero's journey structure, real metrics, and a problem-solution arc that converts prospects better than feature lists.

star 0fork_right 521
bolt
claude-opus-4-6shieldTrusted
bookmark

Cold Outreach Email Writer for B2B SaaS (Personalization-Grounded)

Generates a 3-email cold outreach sequence for B2B SaaS with research-grounded personalization, a single hypothesis-driven value angle, anti-pattern blocklist for spam triggers, and structured A/B variants. Built for AEs and SDRs who refuse to send another templated 'quick question' email.

star 0fork_right 712
bolt
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.