# NovaPath Document Evidence Reader

> NovaPath Document Evidence Reader is a paid API for AI agents from instructional-decision-engine-x402.vercel.app, paid per call via x402, $0.15/call, status unknown (last checked 2026-11-01).

Fetches a public HTML, text, or text-layer PDF URL on demand and returns a concise AI-generated brief with source-matched evidence quotes, retrieval timestamp, source hash, and explicit reading limits

## Facts

- Endpoint: POST https://instructional-decision-engine-x402.vercel.app/ai/document-evidence?utm_source=zero.xyz
- Price: $0.15/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/novapath-document-evidence-reader-3226fa47
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ZJJw_MUqgg_l-v81AreLq

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 novapath-document-evidence-reader-3226fa47 -d '<json body>'
```

Example prompt: Read this public article at https://example.com/report.html — I've confirmed it's a permitted public source — and give me a concise brief with direct evidence quotes pulled from the text, plus the retrieval time and a hash of the source.

## When to prefer this

Choose this endpoint when you need to fetch a specific, known public URL and receive a structured AI brief with source-matched evidence quotes and a source hash for auditability. Ideal for research, fact-checking, and policy work where verbatim citation and provenance (hash + retrieval time) matter. Prefer this over generic web scrapers when you need evidence quotes rather than raw HTML, and over general summarizers when source verification and reading-limit transparency are required.

## Known failure modes

- URL points to a private, paywalled, or non-public resource — request rejected
- URL contains query parameters or fragment identifiers (pattern requires clean HTTPS path) — validation error
- Source requires OCR (image-based PDF) — not supported, returns error
- permissionConfirmed not set to true — request rejected
- Payment verification fails — generation does not begin, no charge settled
- Source content exceeds reading limits — partial brief returned with explicit limit notice
- Network timeout or unreachable URL — retrieval error returned

## How this service works

Read a permitted public HTML, text or text-layer PDF source on demand. Return a concise AI brief with source-matched evidence quotes, retrieval time, source hash and explicit reading limits. No OCR or private URLs. Generation begins only after payment verification; failed generation does not settle.

## Output

A concise AI-generated brief summarizing the fetched document, including verbatim evidence quotes matched to the source text, the exact retrieval timestamp, a hash of the source content for verification, and explicit notes on any reading limits applied. No OCR-derived content; only text-layer or HTML sources are processed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "pattern": "^https://[^?#]+$",
   "maxLength": 1000,
   "minLength": 1
  },
  "permissionConfirmed": {
   "type": "boolean",
   "const": true
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/novapath-document-evidence-reader-3226fa47/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from instructional-decision-engine-x402.vercel.app](https://www.zero.xyz/host/instructional-decision-engine-x402.vercel.app/llms.txt)