# AgentRXI Document Q&A

> AgentRXI Document Q&A is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-15).

Ask a question about any document (web page, PDF, Word, Excel, CSV, or raw text) and receive an answer with exact quotes from the source.

## Facts

- Endpoint: GET https://agentrxi.com/v1/ask?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-document-q-a-489d7a17
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_i3Fc8sLc7LcESE1QooffL

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-document-q-a-489d7a17
```

Example prompt: Can you read this PDF at https://example.com/report.pdf and tell me what it says about Q3 revenue growth, with exact quotes?

## When to prefer this

Use this endpoint when you need a direct, quote-backed answer from a specific document (PDF, Word, Excel, CSV, or web page) rather than a general web search or LLM knowledge. Ideal when accuracy and traceability to source text are required, or when the document is too long for naive context-window stuffing and needs embedding-based retrieval first.

## Known failure modes

- Document URL is inaccessible or returns an error (HTTP 4xx/5xx)
- Document format not supported or cannot be parsed
- Question is too vague to produce a grounded answer
- Document content does not contain information relevant to the question
- Very large documents may timeout or require chunking
- Neither 'url' nor 'text' provided — question alone is insufficient

## How this service works

Ask a document: give a web page, PDF, Word, Excel or CSV URL (or raw text) and a question; get an answer backed by exact quotes from the document. Long documents are searched with embeddings first. Also callable as GET with the same fields as query parameters.

## Output

A natural language answer to the question grounded in the document's content, supported by exact verbatim quotes from the source text. For long documents, relevant sections are retrieved via embeddings before answering.

## 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": [
      "question"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Document or page URL"
      },
      "text": {
       "type": "string",
       "description": "Raw text instead of url"
      },
      "question": {
       "type": "string"
      }
     }
    }
   },
   "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-document-q-a-489d7a17/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)