Customer Case Study
Write a persuasive customer/case-study writeup that turns a customer's results into a credible marketing asset — challenge, solution, and quantified results in the classic before/after arc, with a pull-quote and a clear CTA. Scopes the customer story and the hard metrics FIRST (results without numbers are not a case study), writes the narrative copy in the proven challenge-solution-results structure, then builds a clean, branded single-page HTML asset with a results-highlight band and quote callout. Use for marketing case studies, customer success stories, and sales proof assets.
Steps
Entry step: scope. Each step names the specialist role it wants; the full working prompt is expandable.
- Scope the storyplannerentry
the challenge, the solution, and the quantified results + quote
Show working prompt
Find the story and the proof before writing. Step 1: identify the customer (and their industry/size) and the single headline result that makes this worth publishing. Step 2: map the classic arc: the CHALLENGE (the pain before, ideally with a baseline number), the SOLUTION (what they adopted and how), and the RESULTS (the after, with HARD METRICS — %, time, revenue, scale). Step 3: gather a real customer quote (or note that one is needed) for the pull-quote. Step 4: define the one CTA the asset should drive (demo, contact, signup). Step 5: write an acceptance-criteria checklist ('names the customer + context', 'challenge has a concrete before-state', 'solution is specific', 'results include at least two quantified metrics', 'has a customer pull-quote', 'ends with one clear CTA'). Write the story map + metrics + checklist via write_task_note AND to notes/scope.md. Do not invent metrics — if a number is unknown, mark it as a placeholder to fill, not a fabricated stat. No copy or HTML yet. - Write the narrativecopywriter
challenge -> solution -> results copy with the pull-quote
Show working prompt
Write the case-study copy in the proven structure. Step 1: write a results-led headline and a one-line dek summarizing customer + outcome. Step 2: write a short 'at a glance' summary (industry, the 2-3 key metrics) for skimmers. Step 3: write the Challenge section — set the before-state and stakes concretely. Step 4: write the Solution section — what they did, specifically, and why it fit. Step 5: write the Results section leading with the quantified metrics and what they meant for the business; place the customer pull-quote where it lands hardest. Step 6: write the CTA copy. Keep it credible and specific, not hype; let the numbers do the bragging. Use only the metrics from the scope (no invented stats). Write the section-by-section copy via write_task_note AND to notes/write.md.
- Build the pagedeveloper
render index.html: results band, quote callout, branded styling
Show working prompt
Build the case study as a single self-contained index.html (inline CSS, real branded styling). Step 1: build a header with the results-led headline and dek. Step 2: render an 'at a glance' results band that makes the 2-3 key metrics visually dominant (big numbers, accent color). Step 3: lay out the Challenge -> Solution -> Results sections in order with comfortable reading width and clear section headings. Step 4: render the customer pull-quote as a styled blockquote callout with attribution (name, title, company). Step 5: end with a prominent CTA button. Apply a coherent palette (exact hex) and type scale so it reads as a polished marketing asset, and make it responsive. Drop in the approved copy verbatim; do not invent metrics. On a loop-back, fix ONLY the named gaps. Write the path via write_task_note.
- Evaluatereviewer
Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.
Show working prompt
QA the case study against the locked criteria. Step 1: open/render index.html. Step 2: check EACH acceptance criterion: customer + context named, a results band makes at least two quantified metrics visually dominant, the Challenge has a concrete before-state, the Solution is specific, the Results lead with the metrics, a customer pull-quote with attribution is present, and one clear CTA button closes it. Step 3: confirm the visual styling is real and branded (palette + type applied, not unstyled) and responsive. Step 4: confirm no metrics were invented beyond the scope. Write PASS/FAIL per criterion with the offending section on any FAIL. Then route — this is the whole point of the loop: - **Every criterion PASSES →** call `advance_task_step({ ref, stepId: "evaluate", next: "finish" })`. - **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: "evaluate", next: "build" })` to loop back. The builder fixes exactly those gaps. Never route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in. - Finishdeveloper
All acceptance criteria met. Stamp a short summary and report DONE.
Show working prompt
Every acceptance criterion passed. Write a one-paragraph DONE summary to task notes via `write_task_note`: what was built, the deliverable path(s), and a one-line confirmation that each criterion is met. Then report DONE.
Triggers
Phrases that suggest this craftbook to a crew.
- write a case study
- customer success story
- case study writeup
- customer story
- results story
- case study page
Source
View this craftbook on GitHub · MIT license