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

# How It Works

> VisionAgent + Agent OS architecture.

<img src="https://mintcdn.com/askui-docs-streamline-documentation/i3EQP89EEYHZw2eb/images/infographics/architecture.svg?fit=max&auto=format&n=i3EQP89EEYHZw2eb&q=85&s=acd988d4b021a23708eb4908018582ce" alt="Architecture: Your Code → VisionAgent + LLM → Agent OS" width="800" height="500" data-path="images/infographics/architecture.svg" />

## Components

### VisionAgent

Python SDK that orchestrates tasks. Sends screenshots to LLM, receives actions, executes via Agent OS.

```python theme={null}
from askui import VisionAgent

with VisionAgent() as agent:
    agent.act("Log into the admin dashboard")
```

### Agent OS

Device driver running locally. Provides screen capture, mouse/keyboard control, multi-display support.

### LLM

Understands UI from screenshots, plans actions, executes step-by-step. Configurable—use AskUI's default or bring your own.

## Execution Flow

1. **Screenshot** → Agent OS captures screen
2. **Understanding** → LLM identifies UI elements
3. **Planning** → LLM determines next action
4. **Execution** → Agent OS performs click/type
5. **Loop** → Repeat until task complete

## Why Task-Based?

```python theme={null}
# Traditional (breaks when UI changes)
driver.find_element(By.ID, "email-input").send_keys("test@example.com")

# AskUI (adapts to visual changes)
agent.act('Enter "test@example.com" in the email field')
```

AI understands intent, not implementation. UI changes don't break your automation.