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

# Agent Output

> Control how agents display responses - from silent to verbose with streaming

Output configuration controls how agents display their responses - silent for programmatic use, verbose for interactive sessions, or streaming for real-time feedback.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Output Modes"
        Silent[🔇 Silent<br/>No display]
        Actions[📋 Actions<br/>Tool calls only]
        Verbose[📢 Verbose<br/>Rich panels]
        Stream[🌊 Stream<br/>Real-time]
    end
    
    Silent -->|"API/SDK"| Use[Use Case]
    Actions -->|"Debugging"| Use
    Verbose -->|"Interactive"| Use
    Stream -->|"Chat UI"| Use
    
    classDef silent fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef actions fill:#F59E0B,stroke:#7C90A0,color:#fff
    classDef verbose fill:#10B981,stroke:#7C90A0,color:#fff
    
    class Silent silent
    class Actions actions
    class Verbose,Stream verbose
```

## Quick Start

<Steps>
  <Step title="Default (Silent)">
    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    from praisonaiagents import Agent

    # Default is silent - no output overhead
    agent = Agent(
        name="API Agent",
        instructions="You process data"
    )

    result = agent.chat("Analyze this data")  # Returns result, no display
    ```
  </Step>

  <Step title="Verbose Mode">
    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    agent = Agent(
        name="Interactive Agent",
        instructions="You help users",
        output="verbose"  # Rich panels and formatting
    )

    agent.start("Help me with Python")  # Shows formatted output
    ```
  </Step>
</Steps>

***

## Output Presets

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph TB
    subgraph "Presets"
        S[silent] -->|"Zero overhead"| API[API/SDK Use]
        A[actions] -->|"Tool trace"| Debug[Debugging]
        V[verbose] -->|"Rich display"| Interactive[Interactive]
        J[json] -->|"JSONL events"| Pipe[Piping]
    end
    
    classDef preset fill:#189AB4,stroke:#7C90A0,color:#fff
    classDef use fill:#10B981,stroke:#7C90A0,color:#fff
    
    class S,A,V,J preset
    class API,Debug,Interactive,Pipe use
```

| Preset    | Display                   | Use Case                  |
| --------- | ------------------------- | ------------------------- |
| `silent`  | None                      | Programmatic use, fastest |
| `actions` | Tool calls + final output | Debugging                 |
| `verbose` | Rich panels               | Interactive sessions      |
| `json`    | JSONL events              | Piping to other tools     |

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Preset examples
agent = Agent(instructions="...", output="silent")   # Default
agent = Agent(instructions="...", output="actions")  # Debug
agent = Agent(instructions="...", output="verbose")  # Interactive
agent = Agent(instructions="...", output="json")     # Piping
```

***

## Configuration Options

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import OutputConfig

config = OutputConfig(
    verbose=True,           # Enable verbose output
    markdown=True,          # Format as markdown
    stream=True,            # Enable streaming
    metrics=True,           # Show token metrics
    reasoning_steps=True,   # Show reasoning
    actions_trace=False,    # Tool call trace
    json_output=False,      # JSONL output
    simple_output=False,    # Plain text only
    show_parameters=False,  # Show LLM parameters (debug)
    status_trace=False,     # Clean inline status updates
)
```

| Option            | Type   | Default | Description                 |
| ----------------- | ------ | ------- | --------------------------- |
| `verbose`         | `bool` | `False` | Enable verbose output       |
| `markdown`        | `bool` | `False` | Format as markdown          |
| `stream`          | `bool` | `False` | Enable streaming            |
| `metrics`         | `bool` | `False` | Show token metrics          |
| `reasoning_steps` | `bool` | `False` | Show reasoning process      |
| `actions_trace`   | `bool` | `False` | Show tool calls             |
| `json_output`     | `bool` | `False` | Output JSONL events         |
| `simple_output`   | `bool` | `False` | Plain text without panels   |
| `show_parameters` | `bool` | `False` | Show LLM parameters (debug) |
| `status_trace`    | `bool` | `False` | Clean inline status updates |

***

## Streaming

Real-time output as the agent generates:

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
agent = Agent(
    instructions="You write stories",
    output=OutputConfig(stream=True)
)

# Streams response in real-time
agent.start("Write a short story about AI")
```

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
    participant User
    participant Agent
    participant LLM
    
    User->>Agent: Request
    Agent->>LLM: Generate
    
    loop Streaming
        LLM-->>Agent: Token chunk
        Agent-->>User: Display chunk
    end
    
    Agent-->>User: Complete
```

***

## Verbose vs Silent

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Silent Mode"
        S1[Request] --> S2[Process]
        S2 --> S3[Return]
    end
    
    subgraph "Verbose Mode"
        V1[Request] --> V2[🎨 Panel: Processing]
        V2 --> V3[🔧 Panel: Tool Call]
        V3 --> V4[📝 Panel: Response]
        V4 --> V5[Return]
    end
    
    classDef silent fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef verbose fill:#10B981,stroke:#7C90A0,color:#fff
    
    class S1,S2,S3 silent
    class V1,V2,V3,V4,V5 verbose
```

### Silent (Default)

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Fastest - no display overhead
agent = Agent(instructions="...")
result = agent.chat("Query")  # Just returns result
```

### Verbose

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Rich formatted output
agent = Agent(instructions="...", output="verbose")
agent.start("Query")  # Shows panels, formatting
```

***

## JSON Output

For piping to other tools:

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
agent = Agent(
    instructions="You analyze data",
    output=OutputConfig(json_output=True)
)

# Outputs JSONL events to stderr
# {"event": "llm_start", "model": "gpt-4o", ...}
# {"event": "llm_end", "tokens": 150, ...}
# {"event": "response", "content": "...", ...}
```

***

## Metrics Display

Show token usage and timing:

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
agent = Agent(
    instructions="You help with tasks",
    output=OutputConfig(
        verbose=True,
        metrics=True,  # Show token counts
    )
)

# Output includes:
# Tokens: 150 input, 200 output
# Time: 1.2s
```

***

## Method-Specific Output

Different methods have different default behaviors:

| Method          | Default Output   | Override            |
| --------------- | ---------------- | ------------------- |
| `agent.chat()`  | Silent           | Use `output=` param |
| `agent.start()` | Verbose + Stream | Use `output=` param |
| `agent.run()`   | Silent           | Use `output=` param |

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# chat() is silent by default
result = agent.chat("Query")

# start() is verbose by default
agent.start("Query")

# Override defaults
agent.chat("Query", stream=True)  # Force streaming
```

***

## Best Practices

<AccordionGroup>
  <Accordion title="Use silent for APIs">
    Default silent mode has zero overhead - ideal for programmatic use.
  </Accordion>

  <Accordion title="Use verbose for debugging">
    See exactly what the agent is doing with verbose mode.
  </Accordion>

  <Accordion title="Enable streaming for UX">
    Users prefer seeing progress - enable streaming for interactive apps.
  </Accordion>

  <Accordion title="Use JSON for pipelines">
    JSONL output integrates well with log aggregators and pipelines.
  </Accordion>
</AccordionGroup>

***

## Related

<CardGroup cols={2}>
  <Card title="Streaming" icon="water" href="/features/streaming">
    Real-time output
  </Card>

  <Card title="Execution" icon="play" href="/concepts/execution">
    Execution limits
  </Card>
</CardGroup>