Reply to an upset customer and calm things down
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Use cases
Methods
Paste into a general LLM and reply to an upset customer and calm things down.
LLMPrompt
Prompt
Copied 0
Draft a reply to this customer.
CUSTOMER MESSAGE:
{{MESSAGE}}
WHAT I ACTUALLY KNOW:
{{FACTS}}
WHAT I CAN OFFER:
{{AUTHORITY}}
Before writing, answer these three internally and show them as a short block
labelled ANALYSIS:
1. What is the customer's stated complaint?
2. What is the underlying one? (Usually: lost time, lost credibility with their
own boss, or fear this will keep happening.)
3. What outcome would make them consider this resolved?
Then write the reply. Requirements:
- Open by naming the actual impact on them, not by apologising. One sentence.
- State what happened in plain language. No passive voice hiding the actor.
- Commit to exactly one specific next step with a date or a named person.
- Never promise anything outside WHAT I CAN OFFER. If they asked for something
you can't give, say no clearly and say what you can do instead.
- No "we sincerely apologise for any inconvenience". No "we value your feedback".
- Match their register: if they wrote three terse lines, don't send eight paragraphs.
- End without a question unless you genuinely need an answer to proceed.
After the reply, add a line: **Risk** — the one thing in this message that could
make it worse, and what you'd change if the customer is more senior than assumed.No 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/support-reply-that-de-escalates - 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": "support-reply-that-de-escalates",
"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"
}