Draft customer outage response templates
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Methods
Paste into a general LLM and write phased customer-facing messages for communicating a service outage.
LLMPrompt
Prompt
Copied 0
## Role
You are a crisis communication specialist building a live chat playbook for service outages. Your experience shows customers need three things during disruptions: acknowledgment that you know, honesty about what you don't know, and a clear channel for updates.
## Task
Create a complete outage communication kit organized by crisis phase. Each template must use plain language, never minimize widespread impact, avoid promising timelines you can't guarantee, and support proactive updates every 30 minutes during active outages. Every message should be labeled and ready for immediate deployment.
## Context
**Product & Commitments:**
{{product-and-service-context}}
## Output
Deliver a crisis communication playbook structured as follows:
### Severity Decision Matrix
Present a simple table with three levels (Minor / Major / Critical) showing:
- What qualifies as each severity
- Communication cadence required for each
- Escalation criteria
### Phase 1: First 15 Minutes (Acknowledgment)
Provide 3 chat templates:
1. Customer reports issue before team is aware
2. Known issue, investigation underway
3. Widespread outage confirmed
### Phase 2: Active Outage (Updates)
Provide templates for 30-minute interval updates:
- Update when cause is known
- Update when cause is still unknown
- Update when no change in situation (honest holding pattern)
- Update that references status page
### Phase 3: Resolution (All Clear)
Provide a service-restored message that:
- Confirms the fix
- Acknowledges customer impact
- Explains next steps (monitoring, root cause analysis, SLA credits if applicable)
### Phase 4: Post-Outage (24-Hour Follow-Up)
Provide a follow-up message sent one day later covering:
- What happened in plain language
- What was done to fix it
- What's being done to prevent recurrence
### Special Scenario: Compensation Requests
Provide a response for when customers ask about SLA credits or compensation during an active outage—honest about the process without making promises mid-crisis.
---
**Format:** Clear phase headings, each template labeled and copy-paste ready. Use plain human language, not jargon like "degraded service event." Speak as a human to humans under stress.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/outage-response-templates - 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": "outage-response-templates",
"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"
}