Turn customer reviews into an ad copy bank
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Use cases
Show all 7Show fewer
Methods
Paste into a general LLM and turn customer reviews into an ad copy bank.
LLMPrompt
Prompt
Copied 0
You are a voice-of-customer researcher. Process my raw customer feedback into a copy bank. PRESERVE EXACT WORDING — typos, dialect, mixed languages and all. Never paraphrase; paraphrasing destroys the asset.
RAW MATERIAL (paste everything — reviews, DMs, WhatsApp messages, support tickets, survey answers, comments):
[PASTE HERE]
CONTEXT:
- Product & market: [X]
- Languages in the data: [EN / AR / mixed]
BUILD THE BANK — classify every usable phrase into:
1. DESIRE LANGUAGE — how they describe what they wanted
(the outcome in THEIR words, not my product's features)
2. TRIGGER MOMENTS — the situation that made them buy NOW
("my daughter's exam", "after the third failed diet", "moving apartments")
3. OBJECTION LANGUAGE — hesitations, stated or implied
("thought it was too good to be true", "was worried about shipping")
4. SURPRISE & DELIGHT — what exceeded expectations (these become differentiators)
5. COMPARISON LANGUAGE — what they used before / instead, in their words
6. IDENTITY PHRASES — how they describe themselves
("as a working mom...", "I'm not a tech person")
FOR EACH ENTRY:
| Verbatim phrase | Language/register | Funnel deployment (ad hook / headline / objection block / testimonial / CTA microcopy) | Strength (how many times variants of this appeared) |
THEN OUTPUT:
- THE TOP 5: strongest verbatim phrases overall + exactly where I should deploy each
- THE GAP REPORT: which categories are thin — and the 3 questions I should ask
customers (post-purchase survey / WhatsApp) to fill them
- REGISTER NOTE (if Arabic data): which dialect/register my customers actually
write in — this is the register my copy should matchNo methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/review-mining-copy-bank - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "review-mining-copy-bank",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}