> ## 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.
# Praison AI Agents Playground
> Interactive environment to test and run your AI Agents
Run an Agent in your browser — the playground executes PraisonAI code with no local setup.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
agent = Agent(instructions="You are a helpful assistant")
agent.start("Write a haiku about AI")
```
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Playground"
User[📋 User] --> Editor[🤖 Code Editor]
Editor --> Runner[🧠 Execution Server]
Runner --> Result[✅ Output]
end
classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
classDef output fill:#10B981,stroke:#7C90A0,color:#fff
class User,Editor input
class Runner process
class Result output
```
## How to Use the Playground
1. The code editor is pre-loaded with a simple example using Praison AI Agents
2. Modify the code as needed for your experiments
3. Click "Run" to execute the code and see the results
4. Use the playground to test concepts from the course or your own ideas
## How It Works
You edit code in the browser, the execution server runs it, and the output streams back to the editor.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant User
participant Editor
participant Runner as Execution Server
User->>Editor: Edit and click Run
Editor->>Runner: Send code
Runner-->>Editor: Program output
Editor-->>User: Show result
```
## Best Practices
The editor is pre-loaded with a working snippet. Tweak the `instructions` and prompt before writing from scratch.
The playground is for quick tests. Move larger projects to a local install with `pip install praisonaiagents`.
Try `Agent(...).start("…")` variations to see how instructions and prompts change the output.
## Related
Build your first agent locally.
Learn the core building blocks.