---
title: "Single Agent"
sidebarTitle: "Single"
description: "Learn how to create a basic single-purpose AI agent for simple tasks."
icon: "circle-1"
---

```mermaid
flowchart LR
    In[Input] --> Agent[Single Agent]
    Agent --> Out[Output]
    
    style In fill:#8B0000,color:#fff
    style Agent fill:#2E8B57,color:#fff
    style Out fill:#8B0000,color:#fff
```

A workflow demonstrating how to create and use a simple single-purpose agent.

## Quick Start

<Steps>
    <Step title="Install Package">
        First, install the PraisonAI Agents package:
        ```bash
        pip install praisonaiagents
        ```
    </Step>

    <Step title="Set API Key">
        Set your OpenAI API key as an environment variable:
        ```bash
        export OPENAI_API_KEY=your_api_key_here
        ```
    </Step>

    <Step title="Create Script">
        Create a new file `simple_agent.py`:
        ```python
        from praisonaiagents import Agent

        agent = Agent(instructions="You are a Markdown Agent, output in markdown format")
        agent.start("Write a blog post about AI")
        ```
    </Step>
</Steps>

## Understanding Single Agent

The Single Agent is the simplest form of PraisonAI agent:

1. **Simple Setup**: Minimal configuration required
2. **Single Purpose**: Focused on one specific task
3. **Direct Execution**: Straightforward input-output flow
4. **No Dependencies**: No external tools required

## Features

<CardGroup cols={2}>
  <Card title="Simple Setup" icon="square-1">
    Minimal configuration needed.
  </Card>
  <Card title="Focused Task" icon="bullseye">
    Single-purpose execution.
  </Card>
  <Card title="Quick Start" icon="bolt">
    Rapid implementation.
  </Card>
  <Card title="No Tools" icon="toolbox">
    No external dependencies.
  </Card>
</CardGroup>

## Example Usage

```python
# Example: Create a content generation agent
from praisonaiagents import Agent

# Create content agent
agent = Agent(
    instructions="You are a Content Generation Agent, create engaging content"
)

# Generate content
response = agent.start("""
    Write a short story about:
    - A future world
    - With advanced AI
    - And human collaboration
""")

# Save the story
with open('ai_story.txt', 'w') as f:
    f.write(response)
```

## Next Steps

- Learn about [Prompt Chaining](/features/promptchaining) for more complex workflows
- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving output quality
- Check out other specialized agents like the [Markdown Agent](/agents/markdown) for specific use cases