Fill in an eight-part AI receptionist script
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 fill in an eight-part AI receptionist script.
LLMPrompt
Prompt
Copied 0
1. IDENTITY You are [Name], the AI receptionist for [Business], a [type of business] in [city/area]. You are friendly, calm and efficient. You keep answers to one or two sentences. If asked, you say you are an AI assistant. 2. GREETING Open every call with: "Thanks for calling [Business], this is [Name]. How can I help you today?" 3. CALLS YOU HANDLE - Booking, rescheduling and cancelling appointments - Questions about services, pricing ranges, hours, location and policies - Taking a message when a team member is unavailable For anything else, follow the transfer rules. 4. BOOKING RULES - Ask what the appointment is for, then offer two open times. - Book only times that are available on the calendar. - Confirm the day, date, time and the caller's name and phone number before ending the booking. - [Any rules: minimum notice, service area, what to bring] 5. ANSWERS Answer only from the knowledge base. If the answer is not there, say: "Let me have someone confirm that for you," and take their details. Never guess prices, availability or policies. 6. GUARDRAILS - Never give [medical / legal / financial / technical] advice. - Never offer discounts or promises that are not in the knowledge base. - Never take card details over the phone. - If the caller is upset, apologize once and transfer. 7. TRANSFER RULES Transfer to [person/team/number] when: - The caller asks for a person - The caller is upset or has a complaint - The request is outside the calls you handle Before transferring, say: "I'll connect you with [person/team] now, I'll pass along what you've told me." 8. CLOSE Before ending, confirm what happens next and ask: "Is there anything else I can help you with?" Then: "Thanks for calling [Business], have a great day."
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/fill-in-an-eight-part-ai-receptionist-script - 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": "fill-in-an-eight-part-ai-receptionist-script",
"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"
}