# ManyLives Inbound Reply — AI Customer Message Responder

> ManyLives Inbound Reply — AI Customer Message Responder is a paid API for AI agents from api.manylives.me, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-12).

Generates a contextually appropriate customer service reply grounded in a business's FAQ or policies, with injection detection and intent classification

## Facts

- Endpoint: POST https://api.manylives.me/paid/text/inbound-reply?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/manylives-inbound-reply-ai-customer-message-responder-6001902d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Tu6VBMg3Ps6UfHFmb-_20

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability manylives-inbound-reply-ai-customer-message-responder-6001902d -d '<json body>'
```

Example prompt: A customer just messaged my bike shop Spoke & Chain asking 'Hi, are you open on Sunday? I'd like to bring my bike in for a service.' — can you draft a reply using our FAQ ('We open 9am to 5pm Monday to Saturday, closed Sundays; standard service costs £60 and takes one working day') and keep the tone warm?

## When to prefer this

Choose this endpoint when you need a grounded, policy-faithful customer service reply with built-in safety features (injection detection, source attribution, intent classification) rather than a generic LLM chat call. Ideal for businesses that want to auto-reply to inbound messages using their own FAQ without hallucination risk, and where per-call pricing ($0.004) is preferable to a subscription. Prefer over generic chat APIs when you need the alert_now escalation flag, injection scanning, and explicit answerable/not-answerable signals in a single call.

## Known failure modes

- Customer message exceeds 4,000 character limit — request rejected
- FAQ content exceeds 20,000 character limit — truncation or rejection
- Message is unanswerable from FAQ — answerable:false returned with partial reply
- Prompt injection detected in customer message — injection verdict returns 'flagged' with findings
- Malformed JSON input — HTTP 4xx error
- Payment not included or insufficient — HTTP 402 payment required

## How this service works

Pay-per-call tools for people building AI agents: live web search and page contents, point-in-time crypto market data and news for backtests (no lookahead), verifiable track records of 1,000 crypto strategies locked on the Base network, company profiles, quick AI and batch prices. Ask us to turn a public website into a JSON endpoint. Pay per call, no account, free trial.

## Output

A JSON object containing: a drafted reply string grounded in the FAQ, a quoted excerpt justifying the reply, the customer's intent label, whether the query was answerable from the FAQ, a prompt injection verdict with findings, a boolean alert flag for urgent escalation, and attribution of which model drafted the reply.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "faq": {
   "type": "string",
   "examples": [
    "We open 9am to 5pm Monday to Saturday and are closed on Sundays. A standard bike service costs 60 pounds and takes one working day."
   ],
   "description": "the business's own FAQ or policies as text (up to 20,000 characters), or chunks: [{text, source}] from /paid/web/knowledge-base"
  },
  "tone": {
   "type": "string",
   "description": "optional, e.g. 'warm', 'brief'"
  },
  "chunks": {
   "type": "string",
   "description": "optional list of {text, source}"
  },
  "message": {
   "type": "string",
   "examples": [
    "Hi, are you open on Sunday? I'd like to bring my bike in for a service."
   ],
   "description": "the customer's message (required, up to 4,000 characters)"
  },
  "business": {
   "type": "string",
   "examples": [
    "Spoke & Chain"
   ],
   "description": "optional business name"
  },
  "booking_link": {
   "type": "string",
   "examples": [
    "https://example.com/book"
   ],
   "description": "optional https link to offer for bookings"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "quote": "We open 7am to 3pm, Tuesday to Sunday",
  "reply": "Hi! We're open 7am to 3pm Tuesday to Sunday, and you can book here: https://example.com/book",
  "intent": "booking",
  "source": "faq",
  "alert_now": false,
  "injection": {
   "verdict": "clean",
   "findings": []
  },
  "answerable": true,
  "drafted_by": "open model (llama-3.3-70b)"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/manylives-inbound-reply-ai-customer-message-responder-6001902d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.manylives.me](https://www.zero.xyz/host/api.manylives.me/llms.txt)