Governance Overview

Implement human oversight for your AI agents with flexible governance patterns.

Why Governance?

As AI agents become more autonomous, human oversight becomes critical for:

Safety - Prevent harmful or unintended actions
Compliance - Meet regulatory requirements
Quality - Ensure outputs meet standards
Trust - Build confidence in AI systems
Learning - Improve agents from human feedback

Governance Patterns

TuringPulse supports three governance patterns, each suited for different use cases:

Human-in-the-Loop (HITL)

Require approval BEFORE agent action

Human-after-the-Loop (HATL)

Review and audit AFTER agent action

Human-on-the-Loop (HOTL)

Real-time monitoring with intervention

Comparison

Pattern	When	Latency Impact	Use Case
HITL	Before execution	High (blocks)	High-risk actions, financial transactions
HATL	After execution	None	Quality audits, compliance reviews
HOTL	During execution	None (async)	Real-time monitoring, anomaly response

Quick Start

Enable Governance via SDK

from turingpulse_sdk import instrument, GovernanceDirective

@instrument(
    name="financial-advisor",
    governance=GovernanceDirective(
        hitl=True,
        hatl=True,
        reviewers=["compliance@company.com"],
        escalation_channels=["pagerduty://critical"],
        auto_escalate_after_seconds=3600,
    )
)
def process_transaction(user_id: str, amount: float, action: str):
    return execute_transaction(user_id, amount, action)

Enable Governance via UI

Go to Governance → Policies
Click Create Policy
Select the workflow and governance type
Configure conditions and reviewers
Save and enable the policy

Review Queue

All items requiring human review appear in the Review Queue:

HITL Pending - Actions waiting for approval
HATL Review - Completed actions to audit
HOTL Alerts - Real-time issues requiring attention

Review Actions

Approve - Allow the action to proceed (HITL)
Reject - Block the action (HITL)
Modify - Edit and approve with changes (HITL)
Flag - Mark for follow-up (HATL)
Acknowledge - Confirm review (HATL)

ℹ️

Review Queue Access

Navigate to Governance → Review Queue to see all pending reviews.

Review Policies

Policies define when and how governance is applied:

Policy Configuration

Option	Description
`workflow_id`	Apply to specific workflow or "*" for all
`type`	hitl, hatl, or hotl
`condition`	When to trigger (always, conditional)
`reviewers`	List of reviewer emails or groups
`escalation_channels`	Alert channels for escalation
`auto_escalate_after_seconds`	Seconds before escalation triggers
`severity`	Review priority: low, medium, high

Conditional Governance

Apply governance only when certain conditions are met:

from turingpulse_sdk import GovernanceDirective

# HITL for all runs of a high-risk workflow
governance = GovernanceDirective(
    hitl=True,
    reviewers=["security@company.com"],
    auto_escalate_after_seconds=1800,
    escalation_channels=["pagerduty://critical"],
)

# HATL for post-execution audit
governance = GovernanceDirective(
    hatl=True,
    reviewers=["qa@company.com"],
)

ℹ️

Conditional Governance

To apply governance only when certain conditions are met (e.g., high-cost runs, low-confidence outputs), configure condition-based policies in the TuringPulse UI under Governance → Policies. The SDK marks a workflow for governance; the platform evaluates conditions.

Escalation

Configure escalation for unreviewed items:

governance = GovernanceDirective(
    hitl=True,
    reviewers=["level1@company.com"],
    auto_escalate_after_seconds=1800,
    escalation_channels=["pagerduty://critical", "slack://managers"],
)

💡

Timeout Policies

Auto-approve and auto-reject timeouts can be configured per-workflow in the platform under Governance → Policies.

Review Insights

Track governance metrics and reviewer performance:

Review Volume - Items reviewed per day/week
Review Time - Average time to review
Approval Rate - Percentage approved vs rejected
Escalation Rate - Percentage escalated
Reviewer Load - Distribution across reviewers

Next Steps

Review Policies - Configure policies
Review Queue - Process reviews
HITL - Pre-execution approval
HATL - Post-execution audit
HOTL - Real-time monitoring