Skip to main content
A guardrail is a reusable policy that an owner or admin assigns to a user or an API key. Defines budget, allowed models and providers, ZDR per group, prompt injection and PII detection, and custom content patterns. Managed from /dashboard/guardrails or via the REST API.

​
Components

  • Budget — USD limit per period (daily/weekly/monthly). When the period spend hits the limit, the guardrail blocks until the next reset.
  • Allowed models — allowlist by model id. Empty = all.
  • Allowed providers — allowlist by provider id (openai, anthropic, …).
  • ZDR per group — independent toggle per group. Same concept as the org-level setting but applied per guardrail.
  • Prompt injection detection — regex for common patterns (ignore previous instructions, reveal system prompt).
  • PII detection — off / redact / block. Detects email, phone, RFC, CURP, credit cards, IPv4.
  • Custom patterns — array of { name, pattern, action }. Case-insensitive regex, action redact or block.

​
Combining multiple guardrails

When several apply to the same request:
DimensionRuleExample
Allowed modelsINTERSECTIONA=[gpt5,sonnet], B=[sonnet,opus] → [sonnet]
Allowed providersINTERSECTIONA=[openai,anthropic], B=[anthropic,google] → [anthropic]
ZDR (per group)UNIONIf A requires ZDR for openai, all openai requests require it
BudgetINDEPENDENTAny guardrail with budget-at-limit blocks
Custom patterns + PIIUNION; block > redactA=redact email, B=block email → block
Prompt injectionORIf any enables it, on

​
Block format

HTTP/1.1 403 Forbidden

{
  "error": {
    "type": "guardrail_blocked",
    "message": "Model \"openai/gpt-5\" is not in the allowed-models list for your guardrails."
  }
}
The message describes the high-level reason; it does not expose internal config or individual guardrail names (prevents policy doxing to users without admin permission).

​
REST API

GET    /api/guardrails           # list for current org
POST   /api/guardrails           # create
GET    /api/guardrails/:id       # detail
PUT    /api/guardrails/:id       # full update
DELETE /api/guardrails/:id       # delete (cascades bindings)

​
Example creation

curl -X POST https://app.geekhub.mx/api/guardrails \
  -H "Content-Type: application/json" \
  --cookie "ghub_session=..." \
  -d '{
    "name": "Support team",
    "budgetUsd": 50,
    "budgetPeriod": "monthly",
    "allowedProviders": ["openai","anthropic"],
    "zdrAnthropic": true,
    "piiDetection": "redact",
    "promptInjectionDetection": true,
    "customPatterns": [
      { "name": "no_secrets", "pattern": "(api_key|password)", "action": "block" }
    ]
  }'