Skip to content

Getting Started

Protect sensitive data in your AI applications. This guide gets you from zero to PII-safe AI in under 5 minutes.

Prerequisites

  • Python 3.9 or higher

Step 1: Install the SDK

pip install aegis-sdk

Or with optional dependencies:

pip install aegis-sdk[openai]    # For OpenAI integration
pip install aegis-sdk[anthropic] # For Anthropic integration
pip install aegis-sdk[all]       # All integrations

Step 2: Initialize the SDK

from aegis_sdk import Aegis

# Basic initialization (no license required for core features)
aegis = Aegis()

# Or with a license key for enterprise features
aegis = Aegis(license_key="aegis_lic_xxx")

Step 3: Process Content

Basic Processing

# Process text before sending to AI
result = aegis.process(
    text="Contact [email protected] or call 555-123-4567",
    destination="AI_TOOL"
)

print(f"Decision: {result.decision}")
print(f"Summary: {result.summary}")
print(f"Masked: {result.masked_content}")

Output: 

Decision: Decision.ALLOWED_WITH_MASKING
Summary: Content allowed after masking EMAIL, PHONE
Masked: Contact j***@example.com or call XXX-XXX-4567

Detection Only

# Just detect sensitive data
detected = aegis.detect("Customer SSN: 123-45-6789")

for item in detected:
    print(f"  - {item.type}: {item.count} occurrence(s)")

Masking Only

# Just mask sensitive data
masked = aegis.mask("Email: [email protected]")
print(masked)  # Email: j***@example.com

Step 4: Handle Decisions

Decision Types

Decision Meaning Action
ALLOWED Content is safe Proceed with original
ALLOWED_WITH_MASKING PII was redacted Use result.masked_content
BLOCKED Content violates policy Do not send

Example Handler

from aegis_sdk import Aegis, Decision

aegis = Aegis()

def send_to_ai(content: str) -> str:
    """Safely send content to AI with Aegis protection."""
    result = aegis.process(content, destination="AI_TOOL")

    match result.decision:
        case Decision.BLOCKED:
            raise ValueError(f"Content blocked: {result.summary}")
        case Decision.ALLOWED_WITH_MASKING:
            return call_ai_api(result.masked_content)
        case Decision.ALLOWED:
            return call_ai_api(content)

Step 5: Use LLM Wrappers (Optional)

For the simplest integration, use drop-in replacement clients:

OpenAI

from aegis_sdk import AegisOpenAI

# Drop-in replacement - PII automatically masked
client = AegisOpenAI(api_key="sk-...")

response = client.chat.completions.create(
    model="gpt-4",
    messages=[{
        "role": "user",
        "content": "Customer email: [email protected]"
    }]
)
# OpenAI only sees: "Customer email: j***@example.com"

Anthropic

from aegis_sdk import AegisAnthropic

client = AegisAnthropic(api_key="...")

message = client.messages.create(
    model="claude-3-opus-20240229",
    max_tokens=1024,
    messages=[{
        "role": "user",
        "content": "My SSN is 123-45-6789"
    }]
)
# Claude only sees: "My SSN is XXX-XX-6789"

Complete Example

from aegis_sdk import Aegis, Decision

aegis = Aegis()

# Sample content with sensitive data
content = """
Customer Support Ticket #12345

Customer: Jane Doe
Email: [email protected]
Phone: (555) 123-4567
SSN: 987-65-4321

Issue: Unable to access account. Please reset password.
"""

# Process before sending to AI assistant
result = aegis.process(content, destination="AI_TOOL")

print(f"Decision: {result.decision}")
print(f"Summary: {result.summary}")
print()

if result.detected:
    print("Detected sensitive data:")
    for item in result.detected:
        print(f"  - {item.type}: {item.count} found")

if result.decision == Decision.ALLOWED_WITH_MASKING:
    print("\nMasked content:")
    print(result.masked_content)

Output: 

Decision: Decision.ALLOWED_WITH_MASKING
Summary: Content allowed after masking EMAIL, PHONE, SSN

Detected sensitive data:
  - EMAIL: 1 found
  - PHONE: 1 found
  - SSN: 1 found

Masked content:
Customer Support Ticket #12345

Customer: Jane Doe
Email: j***@example.com
Phone: XXX-XXX-4567
SSN: XXX-XX-4321

Issue: Unable to access account. Please reset password.

CLI Quick Start

The SDK includes a command-line tool:

# Scan for PII
aegis scan "Contact [email protected]"

# Mask PII
aegis mask "My SSN is 123-45-6789"

# Process with policy
aegis process "Customer data here" -d AI_TOOL

# Check version
aegis --version

Next Steps

Troubleshooting

Import Errors

ModuleNotFoundError: No module named 'aegis_sdk'

Solutions:

  1. Ensure you're in the correct virtual environment
  2. Reinstall: pip install --upgrade aegis-sdk
  3. Check Python version: python --version (requires 3.9+)

License Validation Failed

LicenseValidationError: Invalid or expired license key

Solutions:

  1. Verify your license key is correct
  2. Check your internet connection
  3. Use basic mode without license: aegis = Aegis()