CG

Clinical Guard

Deterministic Pre-Generation Safety & Routing

System 1 Local Pre-Filtering + Role-Aware Policy Engine

Zero-PHI-Egress Guardrails for Clinical LLM Applications

clinical-guard sits in front of clinical reasoning LLMs to inspect every incoming prompt locally on CPU before any external API call is made. It combines fast semantic crisis detection, hybrid prompt-injection defense, and ONNX PII anonymization with deterministic role-based routing.

Zero PHI Egress

Safety classification, injection screening, and PII redaction run 100% locally in-cluster. Sensitive patient identifiers never leave your VPC during pre-filtering.

Role-Aware Escalation

Distinguishes layman from medical_professional. Overdose/toxicology queries trigger emergency hotlines for patients, but route to clinical reasoning (with audit flags) for clinicians.

Soft Flag vs. Hard Block

Cosine-margin thresholds separate acute crises (hard_block) from ambiguous medication questions (soft_flag), preventing unnecessary false blocks.

4-Container Microservice Architecture

clinical-guard-api :8000

FastAPI gateway, concurrent pipeline orchestration, deterministic policy matrix, and Showcase UI.

e5-guard :8001

multilingual-e5-small CPU worker for EN/DE crisis & injection anchor similarity.

prompt-guard :8002

Llama-Prompt-Guard-2-86M + delimiter smuggling regex worker.

ner-pii-guard :8003

multilang-pii-ner-ONNX + regex hybrid PII detector & entity table.

Model Selection & Benchmark Explorer

Click any benchmark card to inspect per-row predictions, misclassifications, and EN/DE breakdowns from GET /v1/benchmarks.

Loading benchmark suites...