Skip to main content
Humancheck can be used anywhere you need human oversight for AI agent decisions. The examples below demonstrate common scenarios, but the platform is flexible and can be adapted to any use case where human review, approval, or intervention is needed.

​
What Can You Use Humancheck For?

Humancheck is designed to be framework-agnostic and use-case agnostic. Any scenario where an AI agent needs human oversight can benefit from Humancheck:
  • Financial Operations: Payment approvals, transaction reviews, budget approvals
  • Data Operations: Data deletion, data access requests, data exports
  • Content Management: Content moderation, publishing approvals, editorial reviews
  • System Operations: Database changes, infrastructure changes, deployment approvals
  • Compliance: Regulatory approvals, audit trails, compliance checks
  • Customer Service: Escalation handling, refund approvals, account modifications
  • And Many More: Any scenario where human judgment is needed

​
Example Use Cases

The following pages provide detailed examples for common scenarios:

Payment Approval

Review and approve high-value payments before processing

Data Deletion

Ensure GDPR compliance with human review for data deletion requests

Content Moderation

Human oversight for borderline content moderation decisions

SQL Execution

Review database operations before execution

​
How It Works

Humancheck works with any AI agent or system:
  1. Your AI agent makes a decision or takes an action
  2. When review is needed, the agent requests human review via Humancheck
  3. Human reviewer sees the request in the dashboard (or gets notified)
  4. Reviewer makes a decision: Approve, Reject, or Modify
  5. Decision is returned to your agent, which continues execution

​
Integration Options

You can integrate Humancheck with any system:
  • REST API: Works with any language or framework
  • MCP: Native Claude Desktop integration
  • LangChain/LangGraph: Built-in adapters
  • Custom Adapters: Create your own integration

​
Custom Use Cases

Don’t see your use case? That’s okay! Humancheck is designed to be flexible:
  1. Use the REST API to integrate with any system
  2. Define your own task types (e.g., “custom_review”, “my_use_case”)
  3. Create custom routing rules to route reviews to the right people
  4. Use metadata to pass any context you need

​
Example: Custom Use Case

import httpx

async def my_custom_workflow():
    async with httpx.AsyncClient() as client:
        # Request review for your custom use case
        response = await client.post(
            "https://api.humancheck.dev/reviews",
            headers={
                "Authorization": "Bearer your-api-key-here",
                "Content-Type": "application/json"
            },
            json={
                "task_type": "my_custom_review",  # Your custom task type
                "proposed_action": "Your action description",
                "agent_reasoning": "Why review is needed",
                "confidence_score": 0.75,
                "urgency": "medium",
                "metadata": {
                    # Any custom data you need
                    "custom_field": "value",
                    "context": "additional info"
                },
                "blocking": True  # Wait for decision
            }
        )
        review = response.json()
        
        # Get decision
        decision = review.get("decision")
        if decision["decision_type"] == "approve":
            # Proceed with action
            pass

​
Key Features

Universal Integration

Works with any framework, language, or system

Flexible Routing

Route reviews to the right people based on rules

Blocking & Non-blocking

Wait for decisions or check back later

Full Audit Trail

Track all reviews and decisions

​
Next Steps

Have a unique use case? We’d love to hear about it! Share your use case on GitHub Discussions or Discord.