Docs/Getting Started

Introduction to Tork

Tork is an AI governance platform that provides visibility, control, and compliance for AI agents at scale.

What is Tork?

Tork acts as a safety layer between AI agents and end users, providing comprehensive governance capabilities for autonomous AI systems. As AI agents become more capable and autonomous, organizations need robust tools to ensure they operate within safe and compliant boundaries.

PII Detection

Scan and redact 50+ PII types across 13 countries and 3 industries with regional profiles

Policy Enforcement

Define and enforce governance policies in real-time

Human Oversight

Human-in-the-loop approval workflows for high-risk actions

Cost Controls

Budget governance and spend tracking across providers

Memory Integrity

Trust scoring and drift detection for agent memory

Supply Chain

Dependency tracking and vulnerability scanning

Why Tork?

As AI agents become more autonomous, organizations face new challenges in managing risk, ensuring compliance, and maintaining trust. Tork addresses these challenges by providing:

1

Visibility

Know what your agents are doing with comprehensive audit logs, real-time monitoring, and detailed analytics.

2

Control

Set boundaries and enforce policies across all agents. Define what actions are allowed, require approvals for sensitive operations.

3

Compliance

Meet regulatory requirements with blockchain-anchored audit trails, compliance receipts, and detailed reporting.

4

Trust

Build confidence in AI systems through transparency, predictable behavior, and measurable governance metrics.

TORKING-X Metrics

Tork introduces TORKING-X, a standardized 9-metric system for measuring AI governance health. Each metric is scored 0-100 and weighted to produce an overall governance score.

MetricWeightDescription
TTamper-Evidence10%Audit log integrity and chain verification
PPrivacy Protection15%PII detection and redaction effectiveness
EEphemeral Identity10%Session isolation and credential management
QQuality Guardrails15%Output validation and safety checks
CCircuit Breakers15%Failure handling and recovery mechanisms
SSupply Chain10%Dependency security and verification
LTool Safety10%Tool governance and permission controls
MMemory Integrity10%Memory trust and drift detection
HHITL Enforcement5%Human oversight and approval workflows
TORKING-X Score
Your overall TORKING-X score is a weighted average of all 9 metrics, providing a single number (0-100) that represents your AI governance health. Track your score over time to measure improvement.

Quick Example

Get started with Tork in just a few lines of code:

python
from tork import TorkClient

# Initialize the client
client = TorkClient(api_key="your_api_key")

# Scan content for PII
result = client.pii.scan("Contact john@example.com for details")
print(result['redacted'])  # "Contact [EMAIL] for details"

# Check policy before action
check = client.policy.check(
    agent_id="agent-1",
    action_type="send_email",
    content="Sending confirmation..."
)

if check['allowed']:
    # Proceed with action
    send_email()
else:
    print(f"Blocked: {check['reason']}")

Next Steps