> ## Documentation Index
> Fetch the complete documentation index at: https://docs.humancheck.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> A universal human decisions API for AI agents (HITL ops platform)

## What is Humancheck?

Humancheck is a universal human decisions API for AI agents (HITL ops platform). It enables AI agents to escalate uncertain or high-stakes decisions to human reviewers for approval. It's framework-agnostic, works with any AI system, and provides a complete platform for managing human oversight at scale.

## Humancheck Products

<CardGroup cols={2}>
  <Card title="Humancheck Platform" icon="cloud" href="/platform/overview">
    Managed cloud platform with production-scale infrastructure, ready in minutes. Use `https://api.humancheck.dev` as your base URL.
  </Card>

  <Card title="Humancheck Open Source" icon="code" href="/open-source/overview">
    Self-host the Humancheck stack for full control over data, deployment, and customization. Use your own base URL.
  </Card>
</CardGroup>

## Key Features

### 🔌 Universal Integration

Works with any AI framework via adapter pattern:

* **REST API** - Universal HTTP integration
* **MCP** - Claude Desktop native integration
* **LangChain/LangGraph** - Built-in adapters
* **Mastra** - Framework support
* **Custom adapters** - Extensible for any framework

### 🔗 Platform Integrations

**Platform only:**

* **Built-in Connectors** - Dozens of connectors (Slack, Teams, Discord, etc.) - connect instantly
* **No-Code Tools** - Native integrations with n8n, Zapier, Gumloop, and more
* **Webhooks** - Real-time webhook notifications for review events
* **Multi-User Approval** - Complex approval workflows with multiple reviewers

### 🎯 Intelligent Routing

Route reviews to the right people based on configurable rules:

* Rule-based assignment by task type, urgency, confidence score
* **Open Source**: Config-based routing (YAML)
* **Platform**: UI-based routing with prioritization and fine-grained ACL

### 📊 Real-time Dashboard

Streamlit-based UI for human reviewers:

* Live review queue
* One-click approve/reject/modify
* Statistics and analytics

### 🔄 Flexible Workflows

Support for both blocking and non-blocking patterns:

* **Blocking**: Wait for decision before proceeding
* **Non-blocking**: Continue work, check back later

### 🔧 Flexible Configuration

Simple YAML-based configuration:

* Custom routing rules
* Default reviewers
* Configurable thresholds

### 📈 Feedback Loop

Continuous improvement through feedback:

* Rate decisions
* Comment on reviews
* Track metrics

## Example Use Cases

Humancheck can be used anywhere you need human review or approval. These are just a few examples:

<Columns cols={2}>
  <Card title="Payment Approval" icon="dollar-sign" href="/use-cases/payment-approval">
    Review and approve high-value payments before processing
  </Card>

  <Card title="Data Deletion" icon="trash" href="/use-cases/data-deletion">
    Ensure GDPR compliance with human review for data deletion requests
  </Card>

  <Card title="Content Moderation" icon="shield-check" href="/use-cases/content-moderation">
    Human oversight for borderline content moderation decisions
  </Card>

  <Card title="SQL Execution" icon="database" href="/use-cases/sql-execution">
    Review database operations before execution
  </Card>
</Columns>

<Tip>
  These are just examples! Humancheck can be adapted to any use case where human review is needed. See [all use cases](/use-cases/overview) for more examples and how to create your own.
</Tip>

## How It Works

```
┌─────────────┐
│ AI Agent    │
│ (Any        │
│ Framework)  │
└──────┬──────┘
       │
       │ Request Review
       ▼
┌─────────────┐
│ Humancheck  │
│ API         │
└──────┬──────┘
       │
       │ Routes to
       ▼
┌─────────────┐      ┌──────────────┐
│ Routing     │─────▶│ Human        │
│ Engine      │      │ Reviewer     │
└─────────────┘      └──────┬───────┘
                            │
                            │ Decision
                            ▼
┌─────────────┐      ┌──────────────┐
│ AI Agent    │◀─────│ Decision     │
│ Resumes     │      │ Returned     │
└─────────────┘      └──────────────┘
```

## Quick Example

**Platform (Cloud):**

```python theme={null}
import httpx

async with httpx.AsyncClient() as client:
    response = await client.post(
        "https://api.humancheck.dev/reviews",
        headers={
            "Authorization": "Bearer your-api-key-here",
            "Content-Type": "application/json"
        },
        json={
            "task_type": "payment",
            "proposed_action": "Process payment of $5,000",
            "agent_reasoning": "Payment exceeds auto-approval limit",
            "confidence_score": 0.85,
            "urgency": "high",
            "blocking": True
        }
    )
    review = response.json()
    if review["decision"]["decision_type"] == "approve":
        process_payment()
```

**Open Source (Self-hosted):**

```python theme={null}
import httpx

async with httpx.AsyncClient() as client:
    response = await client.post(
        "http://localhost:8000/reviews",  # Your self-hosted URL
        json={
            "task_type": "payment",
            "proposed_action": "Process payment of $5,000",
            "agent_reasoning": "Payment exceeds auto-approval limit",
            "confidence_score": 0.85,
            "urgency": "high",
            "blocking": True
        }
    )
    review = response.json()
    if review["decision"]["decision_type"] == "approve":
        process_payment()
```

## Integration Options

<CardGroup cols={2}>
  <Card title="REST API" icon="code" href="/integrations/rest-api">
    Universal HTTP integration for any framework or language
  </Card>

  <Card title="MCP (Claude Desktop)" icon="robot" href="/integrations/mcp">
    Native integration with Claude Desktop via MCP protocol
  </Card>

  <Card title="LangChain/LangGraph" icon="link" href="/integrations/langchain">
    Built-in adapters for LangChain and LangGraph agents
  </Card>

  <Card title="Custom Adapters" icon="wrench" href="/integrations/custom-adapters">
    Create your own adapter for any framework
  </Card>
</CardGroup>

## Next Steps

<CardGroup cols={3}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Get started in 5 minutes
  </Card>

  <Card title="API Reference" icon="book" href="/api-reference/introduction">
    Explore the complete API
  </Card>

  <Card title="Use Cases" icon="lightbulb" href="/use-cases/overview">
    See example use cases and create your own
  </Card>
</CardGroup>

***

Made with ❤️ for building safer, more accountable AI systems.