# Verity Suite — Source Reliability Assessment

> Verity Suite — Source Reliability Assessment is a paid API for AI agents from suite.veritylayer.dev, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-15).

Assesses the trustworthiness and reliability of a URL, domain, news outlet, organization, or author, returning a scored verdict with reasons, red flags, and an optional signed receipt.

## Facts

- Endpoint: POST https://suite.veritylayer.dev/source
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-suite-source-reliability-assessment-66e5446b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vPZAsEVjGugKawZZfXRmI

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 verity-suite-source-reliability-assessment-66e5446b -d '<json body>'
```

Example prompt: Can you check how trustworthy Reuters.com is as a source for covering AI regulation news — I need to know if it's reliable before I cite it in my report?

## When to prefer this

Choose this endpoint when an AI agent needs a calibrated, explainable reliability verdict on a specific information source before citing, quoting, or acting on content from it. It is especially valuable when the agent requires a cryptographically verifiable receipt of the assessment, needs explicit red flags rather than a bare score, or is operating in a fail-closed trust environment where unverified sources must be gated. Prefer it over general web search or LLM self-assessment when auditability and a structured trust signal are required.

## Known failure modes

- Unknown or very new domain with no reputation data — verdict returns 'unknown' with minimal reasons
- Malformed or unreachable URL — likely returns an error or 'unknown' verdict
- Source string exceeds 2000 character limit — request rejected with validation error
- Payment not included or insufficient — request blocked (fail-closed, x402 payment required)
- Signing not configured on the engine — receipt field returns null

## How this service works

The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.

## Output

Returns a trust verdict ('trusted', 'mixed', 'untrusted', or 'unknown'), a numeric reliability score from 0 to 1, an array of human-readable reasons supporting the assessment, a list of specific red flags if any, the evidence sources actually consulted, and optionally an Ed25519-signed VerityLayer receipt for cryptographic verification of the result.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "source": {
   "type": "string",
   "title": "Source",
   "maxLength": 2000,
   "minLength": 1,
   "description": "a URL, domain, outlet, org, or author to assess"
  },
  "purpose": {
   "anyOf": [
    {
     "type": "string",
     "maxLength": 2000
    },
    {
     "type": "null"
    }
   ],
   "title": "Purpose",
   "default": null,
   "description": "what the source is being trusted for"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-source-reliability-assessment-66e5446b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from suite.veritylayer.dev](https://www.zero.xyz/host/suite.veritylayer.dev/llms.txt)