# AgentRXI Docs Q&A

> AgentRXI Docs Q&A is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.03/call, status unknown (last checked 2026-10-15).

Crawls a website or documentation (up to 50 pages), indexes it for 7 days, and answers a natural language question with citations to the source pages used.

## Facts

- Endpoint: GET https://agentrxi.com/v1/docs/ask?utm_source=zero.xyz
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-docs-q-a-0897cb8d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_6IxpZUXdE3Qcc98msvFmJ

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 agentrxi-docs-q-a-0897cb8d
```

Example prompt: Crawl the Stripe docs at https://stripe.com/docs and answer this question: 'Does Stripe support ACH transfers for business accounts?' — use up to 30 pages.

## When to prefer this

Use this endpoint when you need to answer a natural language question grounded in a specific website or documentation source that you don't control or can't embed yourself. It is ideal when the target site changes infrequently (7-day index reuse amortizes cost), when you need cited, verifiable answers rather than hallucinated responses, and when you want to avoid building your own RAG pipeline. Prefer this over a general web search when the answer must come specifically from one known domain.

## Known failure modes

- Site unreachable or blocked by robots.txt — crawl fails and no answer is returned
- Question cannot be answered from crawled content — answer may indicate insufficient information
- max_pages limit reached before relevant content found — answer may be incomplete
- Index expired after 7 days — re-crawl required, increasing latency
- Non-English or heavily JS-rendered sites may yield poor text extraction

## How this service works

Ask any website or documentation a question: the site is crawled (up to 50 pages), indexed for 7 days and searched; the answer cites the pages it used. Later questions about the same site reuse the index. $0.03, or $0.05 above 25 pages.

## Output

An AI-generated answer to the question grounded in content crawled from the target site, along with citations to the specific pages that were used to produce the answer. If the site was previously indexed within 7 days, the existing index is reused for faster responses.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "site",
      "question"
     ],
     "properties": {
      "site": {
       "type": "string",
       "description": "Docs or site start URL"
      },
      "refresh": {
       "type": "boolean",
       "description": "true to re-crawl"
      },
      "question": {
       "type": "string"
      },
      "max_pages": {
       "type": "integer",
       "description": "1-50, default 25"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentrxi-docs-q-a-0897cb8d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrxi.com](https://www.zero.xyz/host/agentrxi.com/llms.txt)