# Verity Suite Guardrail Check

> Verity Suite Guardrail Check is a paid API for AI agents from verity-suite.onrender.com, paid per call via x402, $0.08/call, status unknown (last checked 2026-09-13).

Evaluates a proposed agent action against optional policy rules and context, returning a risk score and allow/review/block decision

## Facts

- Endpoint: POST https://verity-suite.onrender.com/check
- Price: $0.08/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-suite-guardrail-check-155f061c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_uK0ehLL5LNF0nFd8f_-pC

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-guardrail-check-155f061c -d '<json body>'
```

Example prompt: Before I proceed, check whether this action is safe: 'transfer $5,000 from the company account to an external wallet', against the policy 'no financial transfers over $1,000 without human approval', in the context of an automated expense processing workflow — give me a risk score and tell me if I should allow, review, or block it.

## When to prefer this

Use this endpoint when your AI agent is about to take an irreversible or high-stakes action and you need a lightweight, pay-per-call safety gate before execution — especially when you have a natural language policy you want enforced. Prefer this over building custom guardrails when you need a calibrated risk score plus a structured allow/review/block decision without standing up your own moderation infrastructure.

## Known failure modes

- Missing required 'action' field returns a validation error
- Overly vague or ambiguous action descriptions may produce low-confidence or inconsistent risk scores
- Service hosted on Render free tier may have cold-start latency or downtime
- Policy strings that conflict internally may produce unpredictable decisions
- Very long context or policy inputs may be truncated or cause errors

## How this service works

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

## Output

Returns a structured object with: a 'decision' field (allow, review, or block), a 'risk' score from 0.0 (clearly safe) to 1.0 (clearly dangerous), a 'reasons' array explaining the decision, an optional 'concerns' array listing specific risks, and an optional 'safer_alternative' string suggesting a lower-risk path when the action is flagged or blocked.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "action"
 ],
 "properties": {
  "action": {
   "type": "string",
   "description": "the action the agent is about to take"
  },
  "policy": {
   "type": "string",
   "description": "rules that must not be violated"
  },
  "context": {
   "type": "string",
   "description": "situation/background"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "title": "guardrail_out",
 "required": [
  "decision",
  "risk",
  "reasons"
 ],
 "properties": {
  "risk": {
   "type": "number",
   "title": "Risk",
   "maximum": 1,
   "minimum": 0,
   "description": "0 = clearly safe, 1 = clearly dangerous"
  },
  "reasons": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Reasons",
   "description": "concrete reasons for the decision"
  },
  "concerns": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Concerns",
   "description": "specific risks noted"
  },
  "decision": {
   "enum": [
    "allow",
    "review",
    "block"
   ],
   "type": "string",
   "title": "Decision",
   "description": "the gate decision"
  },
  "safer_alternative": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "null"
    }
   ],
   "title": "Safer Alternative",
   "description": "a safer path if blocked/flagged"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-guardrail-check-155f061c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from verity-suite.onrender.com](https://www.zero.xyz/host/verity-suite.onrender.com/llms.txt)