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

# Autonomy

> Control how independently your agent operates

Set autonomy levels to control agent independence - from fully supervised to fully autonomous.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Autonomy Levels"
        L[🔒 Low] --> M[⚖️ Medium]
        M --> H[🚀 High]
        H --> F[⚡ Full]
    end
    
    classDef low fill:#EF4444,stroke:#7C90A0,color:#fff
    classDef med fill:#F59E0B,stroke:#7C90A0,color:#fff
    classDef high fill:#10B981,stroke:#7C90A0,color:#fff
    
    class L low
    class M med
    class H,F high
```

## Quick Start

<Steps>
  <Step title="Configure Autonomy">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{AutonomyConfig, AutonomyLevel};

    // Create autonomy configuration
    let config = AutonomyConfig::new()
        .level(AutonomyLevel::Suggest);  // Default - suggests actions, waits for approval

    println!("Level: {:?}", config.level);
    println!("Requires approval: {}", config.require_approval);
    ```
  </Step>

  <Step title="Full Autonomy">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{AutonomyConfig, AutonomyLevel};

    let config = AutonomyConfig::new()
        .level(AutonomyLevel::FullAuto)  // Autonomous operation
        .no_approval()                    // Skip approval prompts
        .max_actions(20);                 // Limit actions per session
    ```
  </Step>

  <Step title="Limited Autonomy with Tool Restrictions">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{AutonomyConfig, AutonomyLevel};

    let config = AutonomyConfig::new()
        .level(AutonomyLevel::AutoEdit)
        .allow_tool("read_file")
        .allow_tool("search")
        .block_tool("delete_file")
        .block_tool("execute_command");
    ```
  </Step>
</Steps>

***

## Choosing Autonomy Level

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph TB
    subgraph "Which Level?"
        Q{Context?} --> |Interactive| S[Suggest - wait for approval]
        Q --> |Supervised| A[AutoEdit - auto with confirm]
        Q --> |Unattended| F[FullAuto - autonomous]
    end
    
    classDef question fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef level fill:#10B981,stroke:#7C90A0,color:#fff
    
    class Q question
    class S,A,F level
```

| Level     | Enum                      | Behavior                                  |
| --------- | ------------------------- | ----------------------------------------- |
| Suggest   | `AutonomyLevel::Suggest`  | Suggests actions, waits for user approval |
| Auto Edit | `AutonomyLevel::AutoEdit` | Auto-edits with confirmation              |
| Full Auto | `AutonomyLevel::FullAuto` | Full autonomous operation                 |

***

## AutonomyConfig

Configuration for agent autonomy behavior.

```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pub struct AutonomyConfig {
    pub level: AutonomyLevel,
    pub require_approval: bool,
    pub max_actions: Option<usize>,
    pub allowed_tools: Vec<String>,
    pub blocked_tools: Vec<String>,
}
```

### Methods

| Method                 | Description                  |
| ---------------------- | ---------------------------- |
| `new()`                | Create with defaults         |
| `level(AutonomyLevel)` | Set autonomy level           |
| `no_approval()`        | Disable approval requirement |
| `max_actions(usize)`   | Set max actions before pause |
| `allow_tool(name)`     | Allow specific tool          |
| `block_tool(name)`     | Block specific tool          |
| `full`                 | No restrictions              |

***

## Configuration

| Option             | Type          | Default  | Description            |
| ------------------ | ------------- | -------- | ---------------------- |
| `level`            | `String`      | `medium` | Autonomy level         |
| `require_approval` | `bool`        | Varies   | Require human approval |
| `allowed_tools`    | `Vec<String>` | All      | Allowed tools          |
| `blocked_tools`    | `Vec<String>` | None     | Blocked tools          |

***

## Best Practices

<AccordionGroup>
  <Accordion title="Start with medium autonomy">
    Balance between productivity and safety. Upgrade when comfortable.
  </Accordion>

  <Accordion title="Use low for testing">
    While developing, use low autonomy to catch issues early.
  </Accordion>

  <Accordion title="Block dangerous tools explicitly">
    For high autonomy agents, explicitly block tools that could cause harm.
  </Accordion>
</AccordionGroup>

***

## Related

<CardGroup cols={2}>
  <Card title="Execution" icon="play" href="/docs/rust/execution">
    Execution limits
  </Card>

  <Card title="Guardrails" icon="shield" href="/docs/rust/guardrails">
    Safety validation
  </Card>
</CardGroup>