# Verity Suite Pro Guardrail Check

> Verity Suite Pro Guardrail Check is a paid API for AI agents from suite.veritylayer.dev, paid per call via x402, $0.2/call, status unknown (last checked 2026-09-14).

Evaluates an AI agent's proposed action against optional policy and context, returning a calibrated allow/review/block decision with risk score and signed receipt

## Facts

- Endpoint: POST https://suite.veritylayer.dev/check/pro
- Price: $0.2/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-suite-pro-guardrail-check-678bb1d4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_18ehgZDRf6MgQLoEBnUUG

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-pro-guardrail-check-678bb1d4 -d '<json body>'
```

Example prompt: Before I proceed, run a Verity guardrail check on this action: 'send $500 USDC to wallet 0xABC on behalf of user' — my policy is 'no transfers over $200 without explicit user confirmation' and the context is 'user asked me to pay their rent'.

## When to prefer this

Choose this endpoint when you need a calibrated, policy-aware safety gate for AI agent actions with a cryptographically signed audit trail. It is particularly well-suited for agentic workflows where fail-closed behavior is required — if the check fails or is uncertain, execution stops. Prefer it over simple rule-based filters when you need nuanced risk scoring, natural-language policy input, and optional verifiable receipts for compliance. The per-call micropayment model makes it practical for high-frequency agent pipelines without subscription overhead.

## Known failure modes

- Missing required 'action' field returns a validation error
- Action or policy text exceeding 2000 characters is rejected
- Invalid HTTP method in the nested input object (only POST/PUT/PATCH accepted)
- Invalid bodyType enum value causes schema rejection
- Payment failure (x402) results in the request not being processed
- Service unavailability returns a fail-closed error (blocked by default)
- Malformed JSON body returns a 400-level error

## How this service works

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

## Output

Returns a JSON object with a 'decision' (allow, review, or block), a 'risk' score between 0 and 1, an array of 'reasons' explaining the decision, an array of 'concerns' listing specific risks, an optional 'safer_alternative' suggestion if blocked or flagged, and an optional Ed25519-signed 'receipt' object from VerityLayer for audit verification.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "action": {
   "type": "string",
   "title": "Action",
   "maxLength": 2000,
   "minLength": 1,
   "description": "the action the agent is about to take"
  },
  "policy": {
   "anyOf": [
    {
     "type": "string",
     "maxLength": 2000
    },
    {
     "type": "null"
    }
   ],
   "title": "Policy",
   "default": null,
   "description": "rules that must not be violated"
  },
  "context": {
   "anyOf": [
    {
     "type": "string",
     "maxLength": 2000
    },
    {
     "type": "null"
    }
   ],
   "title": "Context",
   "default": null,
   "description": "situation/background"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-pro-guardrail-check-678bb1d4/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)