✍️ Writing
B2B Case Study Writer from Customer Notes
Convert messy customer interview notes into a publishable case study: challenge, solution, results, quotes, and a one-page sales cut. No invented metrics.
0Reviews
Prompt
Act as a B2B customer-marketing writer who turns interview notes into a case study a sales team will actually send. Keep every number and quote traceable to the notes. If a result is missing, leave a hole. Do not fill holes with typical SaaS numbers. Inputs: - Customer company: [Customer] - Customer person: [Name, title] - Our product: [Product] - Interview notes: [Notes] - Numbers I can publish: [Numbers] - Quotes I can use verbatim: [Quotes] - Sensitive / cannot publish: [Off record] - Industry and company size: [Industry, size] - Use case: [Use case] - CTA for readers: [CTA] - Length: [Short 700 / Standard 1100 / Long 1600] - Anonymize?: [Yes / No] - Voice: [Plain / Formal] Generate: 1. Approval flags: List every metric, name, and logo that must be confirmed before this goes live. Mark invent-risk if the notes are thin. 2. Angle: One sentence. The job the customer hired us for, not a product brochure. Three title options. Mark recommended. 3. Full case study in this structure, at Length: - Title and dek - Snapshot box: customer, industry, size, product, use case, 3 results (only from Numbers) - Challenge: the old way, cost of the old way, trigger to look - Why us: 2-4 reasons from the notes, not a feature dump - Solution: what they implemented, who used it, timeline if given - Results: each number with the baseline and the time window from Inputs. No extra math. - Quote block: only verbatim Quotes. If none, write "no approved quote" instead of paraphrasing a hero line - What is next: only if the notes say it - CTA 4. Pull quotes (3) and a 40-word sales one-pager. 5. Social blurbs: LinkedIn (120-180 words), tweet (240 chars), email subject (3). 6. Sales objection map: 4 objections this story does not answer. Do not stretch the story to answer them. 7. Redlines: lines you refused to write (anonymize, off-record, missing math). Constraints: - Do not invent ROI, payback, headcount saved, or logos. - Do not upgrade "we think" into "they achieved." - Quotes stay verbatim. You may trim with ellipses, not rewrite. - If Anonymize is Yes, use role and industry only. - No "journey," "delighted," or "partnered with us to transform." - Honor Off record even if it was the best line.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Examples
Example Input
Customer company: Northwind Outfitters Customer person: Priya Shah, VP Operations Our product: Routefold, last-mile routing for regional retailers Interview notes: They had 18 stores in Ohio and Indiana. Dispatch lived in a whiteboard and three group texts. Drivers started late because stops were reordered by phone. Priya's team tried a spreadsheet with drive-time guesses; it died in week two. They ran Routefold on 6 stores in Jan 2026, all 18 by March. Dispatch is now two people in the morning, not five. Drivers still complain about the mobile map in parking garages. They do not want us to name the old TMS they almost bought. Priya said they will not talk publicly about fuel cost. Numbers I can publish: on-time window (promised 2-hour slot) 71% to 89% after 90 days on all 18 stores; average stops per driver per day 16 to 19; dispatch headcount on the morning shift 5 to 2 (roles moved to store ops, not laid off). Quotes I can use verbatim: "The whiteboard was the source of truth until it wasn't." "I did not need another dashboard. I needed the stops in an order a driver would actually run." Sensitive: fuel savings, the competing TMS name, any layoff implication Industry and size: regional outdoor retailer, 18 stores, ~420 employees Use case: last-mile delivery from store, not warehouse CTA: book a 20-min routing review Length: Short 700 Anonymize?: No Voice: Plain
Example Output
1. Approval flags Confirm before live: Northwind Outfitters name and logo; Priya Shah, VP Operations; 18 stores, Ohio and Indiana; 71% to 89% on-time in a 2-hour slot after 90 days on all 18 stores; 16 to 19 stops per driver per day; morning dispatch 5 to 2 with the "moved to store ops, not laid off" line; Jan 2026 six-store pilot, all 18 by March; both verbatim quotes. Invent-risk: none on the numbers (they were provided). Still missing: any fuel figure (do not add). Competing TMS: do not name. 2. Angle Northwind hired Routefold to put store-based last-mile stops in an order drivers would run, and to get the whiteboard out of the morning. Titles: * How Northwind Outfitters moved last-mile dispatch off the whiteboard Northwind Outfitters: 71% to 89% on-time after 90 days on Routefold Two dispatchers, 18 stores: Northwind's last-mile routing change 3. Case study (short) Title: How Northwind Outfitters moved last-mile dispatch off the whiteboard Dek: An 18-store outdoor retailer replaced group texts and a whiteboard with Routefold. On-time windows rose from 71% to 89% in 90 days. Snapshot Customer: Northwind Outfitters, regional outdoor retail, 18 stores, ~420 employees Product: Routefold Use case: last-mile from store, not warehouse Results: on-time 71% to 89% (2-hour slot, 90 days, 18 stores); stops/driver/day 16 to 19; morning dispatch 5 to 2 (roles moved to store ops) Challenge Dispatch for 18 Ohio and Indiana stores lived on a whiteboard and three group texts. Drivers started late because stops were reordered by phone. A spreadsheet of drive-time guesses died in week two. Why Routefold Priya did not want another dashboard. She wanted stop order a driver would run. Store-based delivery, not a warehouse model. Six stores in Jan 2026, all 18 by March. Solution Routefold now builds the morning routes. Two people run dispatch in the morning, not five. The other three roles moved into store ops. They were not laid off. Drivers still complain about the mobile map in parking garages. That is in the notes. It stays in the story. Results - On-time inside the promised 2-hour slot: 71% to 89%, 90 days, all 18 stores. - Stops per driver per day: 16 to 19. - Morning dispatch: 5 to 2, with the move to store ops named so this is not read as cuts. Quotes "The whiteboard was the source of truth until it wasn't." "I did not need another dashboard. I needed the stops in an order a driver would actually run." Priya Shah, VP Operations Next: not in the notes. Omit. CTA: Book a 20-minute routing review. 4. Pull quotes / one-pager "The whiteboard was the source of truth until it wasn't." "I needed the stops in an order a driver would actually run." On-time 71% to 89% in 90 days, 18 stores. Sales one-pager (40 words): Northwind Outfitters, 18 stores, ran last-mile off a whiteboard. Routefold, store-based. 71% to 89% on-time in 90 days. 16 to 19 stops per driver. Morning dispatch 5 to 2, roles moved, not cut. 5. Social LinkedIn: Northwind Outfitters had 18 stores and a whiteboard that was the routing system. Group texts reordered stops after vans left. They put six stores on Routefold in Jan 2026 and all 18 by March. On-time in a 2-hour slot: 71% to 89% in 90 days. Stops per driver: 16 to 19. Morning dispatch went from five people to two. The other roles moved to store ops. Priya Shah, VP Operations: "I did not need another dashboard. I needed the stops in an order a driver would actually run." Tweet: Northwind Outfitters: whiteboard dispatch to Routefold. On-time 71% to 89% in 90 days. 18 stores. Subjects: Northwind's whiteboard problem; 71% to 89% on-time, 18 stores; Two dispatchers, 18 stores 6. Objections this story does not answer Fuel savings (off record). Warehouse-origin routing. Named TMS bake-off. Parking-garage map quality (drivers still complain; not a win). 7. Redlines Refused: fuel dollars; competitor TMS name; layoffs or efficiency cuts; extra ROI math; paraphrased hero quote.