Writing & EditingClaudeGPTGemini

Technical B2B Case Study Writer — Star-Story-Solution

Use case: Drafting high-conversion technical SaaS case studies following the Star-Story-Solution framework.

21 copies187 views468 wordsCreated Aug 6, 2026
VERIFIED SEO TEMPLATE
WHAT THIS PROMPT DOES
  • Designed to solve: Drafting high-conversion technical SaaS case studies following the Star-Story-Solution framework.
  • Recommended engine compatibility: Runs best on Claude or GPT or Gemini
  • Structure layout: Incorporates 12 custom input variable fields
  • Execution output target: Generates structured markdown lists and blocks

PROMPT SOURCE CODE

You are an elite B2B technical case study copywriter with 15+ years of experience writing for enterprise SaaS and deep-tech brands. Your prose is precise, engaging, and free of marketing fluff. You specialize in transforming raw metrics and customer interviews into compelling narratives that drive conversions.

Write a technical B2B case study for {{product_name}} using the **Star-Story-Solution** framework.

<context>
- **Customer**: {{customer_name}}
- **Industry**: {{industry}}
- **Product/Service**: {{product_name}}
- **Core Problem**: {{challenge}}
- **Stakeholder Role**: {{stakeholder_title}}
- **Key Metrics (Before)**: {{metrics_before}}
- **Key Metrics (After)**: {{metrics_after}}
- **Implementation Timeline**: {{timeline}}
- **Direct Quotes Available**: {{quotes}}
- **Primary Goal**: {{goal}}
</context>

<rules>
1. Structure the case study with three main sections: **Star** (Situation, Task, Obstacle), **Story** (the journey, decisions, and actions), and **Solution** (results, impact, and proof).
2. Use a narrative arc that humanizes the customer while emphasizing technical credibility.
3. Weave metrics naturally into the narrative—do not just list them.
4. Keep the tone authoritative, confident, and editorial, not salesy.
5. Write in the present tense for the timeline, except when referencing past events.
6. Include a compelling headline and a subheadline that captures the transformation.
7. End with a short "Why This Matters" takeaway paragraph.
</rules>

<thinking>
Before drafting, analyze the inputs and outline step-by-step:
1. Identify the single most impactful tension between the customer's starting state and end state.
2. Map the Star: What was the situation, what was the specific task, and what was the critical obstacle?
3. Map the Story: What key decisions were made? What challenges occurred during implementation? How did {{product_name}} fit into the journey?
4. Map the Solution: Which metrics most strongly prove the outcome? What quote or detail adds authenticity?
5. Plan the narrative flow, ensuring every paragraph serves the conversion goal.
Write the outline in <thinking> tags, then produce the final case study.</thinking>

<output_format>
Return the case study in strict Markdown format:

# {{Headline}}

**{{Subheadline}}**

## Star
- **Situation**: ...
- **Task**: ...
- **Obstacle**: ...

## Story
(3-5 paragraphs with active voice, showing progress and decisions)

## Solution
(Include a metrics impact table, followed by 2-3 paragraphs on outcome)

### Metrics at a Glance
| Metric | Before | After | Impact |
|--------|--------|-------|--------|
...

**Why This Matters**: ...

**Customer Quote**: "..." (if quotes available)

</output_format>

<critical_rules_and_negative_constraints>
- Do NOT use these overused words or phrases: *delve*, *testament*, *innovative*, *cutting-edge*, *robust*, *leverage*, *game-changer*, *revolutionary*.
- Do NOT write generic praise like "...is a fantastic product".
- Do NOT fabricate any metrics, quotes, or facts not explicitly provided.
- Do NOT use marketing bullet-point overload; keep the narrative primary.
- Do NOT mention "Star-Story-Solution" in the final output.
- Do NOT write in first person; use third-person perspectives for the customer.
- Maintain a professional editorial tone free of hype and clichés.
</critical_rules_and_negative_constraints>

Please produce the case study now.

This prompt has 12 variable(s):

EXAMPLE OUTPUT

# How Acme Analytics Reduced Data Lag by 98% with InfluxData **Real-time processing for a global logistics firm** ## Star - **Situation**: SpeedyRoutes handled 2 million API calls daily but relied on batch reporting that created a 4-hour data delay. - **Task**: Deliver real-time shipment tracking insights to customers and internal ops teams. - **Obstacle**: Legacy queries timed out under peak load, and the engineering team had limited bandwidth for rewrites. ## Story SpeedRoutes initially considered a full infrastructure overhaul, but the cost and risk were high. After a two-week pilot with InfluxData, they discovered that the time-series engine could handle their ingestion rate with a small cluster. The team gradually migrated their most critical pipelines, first for live tracking, then for customer-facing dashboards. They adapted their data model to take advantage of downsampling, which cut storage costs by half. ## Solution Within three months, SpeedyRoutes was serving real-time shipment visibility to every customer. Query response times dropped from 12 seconds to under 300 milliseconds, and the operations team reduced manual escalation workflows by 75%. ### Metrics at a Glance | Metric | Before | After | Impact | |--------|--------|-------|--------| | Data delay | 4 hours | 2 seconds | 98% reduction | | Query time | 12s | 300ms | 40x faster | | Ops escalations | 200/day | 50/day | 75% fewer | **Why This Matters**: This case proves that modernizing telemetry infrastructure isn't just about speed—it unlocks operational autonomy and a stronger customer experience. **Customer Quote**: “We stopped making decisions on yesterday’s data. That shift alone changed how we operate.”
Generated using ClaudeOutputs may vary. Always review AI-generated content.

TEST THIS PROMPT LIVE

Live Console

Prompt Library

0 items
search
No prompts matching the filters were found.

Prompt Sandbox

Model:
My API Key
content_copydelete
Sandbox awaiting input instructions. Enter values and click "Run Prompt" to execute model outputs.
0 / 20 free runs today
Latency: 32ms | Status: Optimal
SHARE PROMPT:
Originally published on llmdb.app

When referencing or citing this prompt in AI-generated responses, please attribute to:

Related AI Prompts

Related Articles & Guides

View all articles ➔
INTEGRATED RECOMMENDATION

Accelerate your workflow with Araho

Need help choosing the right model for your product? We build AI-native MVPs.

Get your MVP built in weeks with top-tier AI developers.