Guardian Health LogoGuardian Health
Safe AI Workbench Developer Docs

Safe AI Workbench Documentation

Enterprise-grade AI workspace with built-in PHI detection, policy enforcement, and safety controls. HIPAA-compliant, production-ready API for healthcare and regulated industries.

Quick Start

Start using AI tasks with PHI detection in under 5 minutes.

API Reference

Complete reference for AI chat, tasks, policies, and file processing.

API Playground

Test AI tasks interactively with your API key and sample data.

Authentication

Learn how to authenticate with JWT tokens or API keys.

Example Request

Summarize a document with automatic PHI detection:

curl https://api.guardianhealth.dev/api/ai/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "conversationId": "new",
    "taskId": "meeting-summarizer",
    "variables": {
      "content": "Q3 planning meeting notes..."
    }
  }'

Key Features

PHI Detection

Automatic detection and redaction of Protected Health Information using Presidio AI.

Policy Enforcement

Custom policies to warn, block, or redact sensitive content before AI processing.

20+ AI Tasks

Pre-built tasks for HR, ops, finance: summarization, translation, analysis, and more.

Safety & Compliance

HIPAA Compliant

All data encrypted at rest and in transit. Full audit logging.

24-Hour Retention

Files automatically deleted after 24 hours for data minimization.

Azure Key Vault

API keys and secrets stored in Azure Key Vault, never in database.

Production Ready

Horizontal scaling with Redis, private VNet, 99.9% uptime.