AIO Apex
en
Claude Sonnet 4.6 or GPT-5.4 (needs strong long-context synthesis to avoid fabricating details not in the source material). Gemini 2.5 Pro works as an alternative. Avoid smaller/faster models — hallucination risk is the main failure mode this prompt guards against.A product marketer at a 60-person B2B SaaS company just got off a call with a happy customer whose renewal came in at 140% of their original contract value. The customer success rep forwarded three Slack messages, a call transcript, and a usage dashboard screenshot — but no one has time to turn that into a polished case study before the sales team's QBR next week, and the marketer doesn't want to misquote the customer or invent numbers that could embarrass the company if the customer ever reads the published piece.marketing

The Case Study Harvester: Turn a Customer Win Into a Case Study That Sells Itself

Share:
The Case Study Harvester: Turn a Customer Win Into a Case Study That Sells Itself

Why this prompt matters

Case studies are the single highest-converting asset in B2B sales enablement — reps report closing deals faster when they can point to a specific, similar customer's results — but most marketing teams produce fewer than one a month because assembling one from scattered source material (call notes, screenshots, Slack) typically takes 4-6 hours of a marketer's time. That bottleneck means dozens of strong customer stories go uncaptured, and expansion or renewal moments that would make the best case studies get missed entirely while the details are still fresh.

What we use it for

A product marketer at a 60-person B2B SaaS company just got off a call with a happy customer whose renewal came in at 140% of their original contract value. The customer success rep forwarded three Slack messages, a call transcript, and a usage dashboard screenshot — but no one has time to turn that into a polished case study before the sales team's QBR next week, and the marketer doesn't want to misquote the customer or invent numbers that could embarrass the company if the customer ever reads the published piece.

Prompt

Role: Act as a senior B2B content marketer who has written over 100 published customer case studies for SaaS and B2B companies.

Context:
[PASTE RAW CUSTOMER WIN MATERIAL HERE — e.g., sales call notes, customer success team Slack messages, usage metrics, direct customer quotes, renewal or expansion details]
The customer is: [CUSTOMER COMPANY NAME AND INDUSTRY]
Our product/solution is: [YOUR PRODUCT NAME AND ONE-LINE DESCRIPTION]
The primary audience for this case study is: [TARGET BUYER PERSONA, e.g. "VP of Operations at mid-market logistics companies"]

Task: Using only the facts present in the raw material above, produce a complete case study draft that:
1. Opens with a specific, quantified result in the first two sentences — not a generic "X improved their process" opener
2. Identifies the customer's «before» state — the specific pain, workaround, or cost they were living with
3. Explains the decision process — why they chose this solution over alternatives, if that information exists in the source material
4. Walks through implementation and the specific ways the product was used
5. States results with real numbers wherever the source material provides them, and flags clearly with [NEEDS VERIFICATION: metric] any number you are inferring or estimating rather than one stated directly in the source
6. Includes at least one direct, attributed quote pulled verbatim from the source material — do not fabricate a quote
7. Closes with a forward-looking statement about what the customer plans to do next, if mentioned in the source

Constraints:
- Do not invent any statistic, metric, or quote that does not appear in the source material. If a result is stated vaguely (e.g., "a lot faster"), keep it vague rather than assigning it a fabricated number
- Avoid marketing clichés: no «revolutionize,» «game-changing,» «seamless,» or «unlock your potential»
- Keep sentences short enough to skim — assume the reader is a busy prospect comparing three vendors
- Do not exceed [TARGET WORD COUNT, e.g. 600] words for the main narrative
- Flag any claim about ROI or cost savings that isn't directly supported by a number in the source material

Output Format:
- Headline (one line, states the core result)
- Subheadline (one line, names the customer and their industry)
- «The Challenge» section (2-3 short paragraphs)
- «The Solution» section (2-3 short paragraphs)
- «The Results» section (bulleted, numbers-first)
- One pull-quote, attributed with name/title if available in source
- «What's Next» closing section (2-3 sentences)
- A separate list titled «Unverified Claims to Check With Customer» listing every [NEEDS VERIFICATION] flag raised during drafting

Result

Headline: Northwind Logistics Cut Dispatch Reassignment Time by 63% and Renewed at 140% of Contract Value

Subheadline: How a 40-truck regional logistics fleet replaced three disconnected systems with one dispatch workflow

The Challenge

Before adopting the platform, Northwind Logistics' dispatch team coordinated incoming load requests across a shared spreadsheet, a separate driver-texting app, and a whiteboard in the dispatch office. When a truck broke down or a delivery window shifted, reassigning a load meant a dispatcher manually cross-referencing all three systems — a process that averaged 22 minutes per reassignment during peak hours, according to the company's own internal tracking.

With 40 trucks running regional routes six days a week, that friction compounded. Dispatchers were fielding an average of 15 reassignments per shift, meaning roughly five and a half hours of dispatcher time each day went to reconciling systems rather than actually routing freight.

The Solution

Northwind rolled out the platform across its primary depot in March, consolidating load requests, driver communication, and real-time route status into a single dispatch view. The team specifically used the automatic reassignment-suggestion feature to surface the nearest available truck when a load needed to move, rather than requiring a dispatcher to manually check driver locations across the old whiteboard system.

The Results

  • Dispatch reassignment time dropped from an average of 22 minutes to approximately 8 minutes per incident — a 63% reduction
  • Missed delivery windows decreased, though Northwind has not shared an exact percentage [NEEDS VERIFICATION: missed-delivery reduction percentage]
  • Northwind renewed at 140% of its original contract value, adding licenses for a second depot

«We didn't realize how much dispatcher burnout was coming from switching between three systems until we didn't have to anymore,» said the Director of Operations at Northwind Logistics.

What's Next

Northwind is piloting the mobile driver app at its second depot in Q1, with plans to expand the automatic reassignment feature to overnight shifts if the pilot confirms the same time savings.

Unverified Claims to Check With Customer:

  • [NEEDS VERIFICATION: missed-delivery reduction percentage] — source material only mentioned «fewer missed deliveries» without a specific number

Case studies are supposed to be fast, low-cost proof points — but most marketing teams produce fewer than one a month, because turning a customer win into a polished narrative means digging through call notes, Slack threads, and dashboard screenshots, then writing a draft nobody can verify against the original conversation. This prompt is built to close that gap without inventing anything.

The Role section anchors the output in B2B case-study conventions — the standard «challenge, solution, results» arc that buyers expect — rather than generic marketing copy. The Context block is deliberately raw: you paste in whatever messy material you actually have, rather than pre-summarizing it yourself, because pre-summarizing is where details get lost or exaggerated before the model even sees them.

The Task section's seven steps exist because case studies fail in a specific, predictable order: vague openers that bury the result, missing «before» context that makes the «after» meaningless, and an overly earnest tone that reads like every other case study on the internet. Numbering the steps forces each one to get addressed rather than skipped under time pressure.

The most important line in the whole prompt is the Constraints instruction to flag fabricated or inferred numbers with [NEEDS VERIFICATION] instead of inventing them outright. Case studies get published, sent to legal and the customer for approval, and sometimes read by that customer's competitors — a single invented statistic the customer later disputes can cost you the account, not just the case study. The separate «Unverified Claims to Check» output section turns that constraint into a checklist a marketer can resolve with one follow-up email instead of hoping no one notices.

B2Bmarketingcontent-marketingcase studysales-enablement
Share: