# Verity Suite Quick Guardrail Check

> Verity Suite Quick Guardrail Check is a paid API for AI agents from verity-suite.onrender.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Evaluates an 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/quick
- Price: $0.02/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-quick-guardrail-check-73ad11e7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_w1Oo2T1_C5-3GyzQHMwp2

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-quick-guardrail-check-73ad11e7 -d '<json body>'
```

Example prompt: Before I proceed, run a quick guardrail check on this action: 'send a bulk email to all 5,000 users offering a 50% discount coupon' — my policy is 'no mass communications without human approval' and the context is that I'm an autonomous marketing agent running overnight campaigns.

## When to prefer this

Use this endpoint when an AI agent needs a fast, per-action risk gate before executing potentially harmful or policy-violating steps. It is ideal for fail-closed architectures where uncertain actions should default to blocked or reviewed. Prefer this over a custom LLM prompt-based check when you need a structured, scored, auditable response with explicit reasons and a safer-alternative suggestion, and when you want to pay only per call rather than maintain your own safety model.

## Known failure modes

- Missing required 'action' field returns a validation error
- Ambiguous or very short action strings may produce low-confidence decisions
- Network timeouts possible if the Render.com host is cold-starting
- Overly broad policy strings may result in overly conservative 'block' decisions
- Context field left empty may reduce decision accuracy for nuanced actions

## How this service works

Guardrail: pre-action safety: allow / review / block Calibrated, fail-closed AI-safety service for agents — honest 0-1 confidence, abstains rather than guess.

## Output

Returns a JSON object with a 'decision' field (allow, review, or block), a 'risk' score from 0 to 1 (0 = clearly safe, 1 = clearly dangerous), a 'reasons' array explaining the decision, an optional 'concerns' array listing specific risks, and an optional 'safer_alternative' string suggesting a less risky path if the action is flagged or blocked.

## 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-quick-guardrail-check-73ad11e7/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)