llmcloud.ai
Platform · Guardrails

Policy at the edge, not in your prompts.

PII redaction, prompt-injection blocking and content policies run at the router — before traffic hits a provider. Global toggles, per-key overrides.

MVP · join waitlist
pii

PII redaction

Detect and mask names, emails, phones, cards and national IDs. Re-inject on response for the caller only.

prompt-inj

Prompt injection

Classifier scores every user turn and tool result. Block, warn, quarantine or reroute to a hardened model.

content

Content safety

OpenAI moderation, Llama Guard, or your own classifier. Per-category thresholds for violence, self-harm, sexual and hate.

rules

Custom rule engine

Deny by regex, allow-list retrieved domains, cap request size, require a system prompt prefix.

compliance

Zero-retention routing

Route only to providers with signed zero-retention terms. Non-compliant peers are dropped.

audit

Signal in every response

x-llmcloud-guardrail lists every rule that fired, with a policy_id you can trace in the audit log.

Configure a policy
POST /v1/policies
{
  "name": "prod-default",
  "pii": { "action": "redact", "scope": ["email","phone","ssn"] },
  "injection": { "action": "block", "threshold": 0.7 },
  "content": {
    "provider": "llama-guard-4",
    "block": ["violence","self_harm"],
    "warn": ["sexual"]
  },
  "routing": { "require_zero_retention": true }
}
Attach to a key or a request
# Per-key (default policy for all requests on this key)
PATCH /v1/keys/agent-prod-router
{ "policy": "prod-default" }

# Per-request override
POST /v1/chat/completions
Headers:
  X-LLMCloud-Policy: prod-default
Body:
  { "model": "auto:quality", "messages": [...] }
How much latency do guardrails add?+

PII and injection classification run in parallel with routing — 6–14ms p50 overhead. Content classifiers on the response can run async for streaming.

Can I bring my own classifier?+

Yes. Point a rule at your webhook; the router calls it inline with a configurable timeout and fallback.

Do redactions round-trip?+

Optionally. Ingress maps tokens to synthetic placeholders; the router re-inflates on egress. Nothing sensitive touches the upstream.