# Quick Start

Get up and running with AG2 in just **3 minutes**! This guide will help you set up your environment and build your very first agent workflow.

## Prerequisites

Make sure you've [installed AG2](https://docs.ag2.ai/0.13.2/docs/user-guide/basic-concepts/installing-ag2/) before continuing. Need just 30 seconds for your provider of choice:

- [OpenAI](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_1_1)
- [Gemini](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_1_2)
- [Azure OpenAI](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_1_3)

```bash
pip install "ag2[openai]"
```

```bash
pip install "ag2[gemini]"
```

```bash
pip install "ag2[openai]"
```

### Set Up Your Environment

**Python Version**

AG2 requires **Python version >= 3.10, < 3.14**. We recommend using a virtual environment for your project to keep your packages contained. See [venv](https://docs.python.org/3/library/venv.html).

**Set Your API Key**

Make sure to set your LLM API key (and any provider-specific endpoint values) as environment variables. Pick the provider you plan to use:

- [OpenAI](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_2_1)
- [Gemini](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_2_2)
- [Azure OpenAI](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_2_3)

- [macOS / Linux](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_3_1)
- [Windows](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_3_2)

```bash
export OPENAI_API_KEY="YOUR_API_KEY"
```

```bash
setx OPENAI_API_KEY "YOUR_API_KEY"
```

- [macOS / Linux](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_4_1)
- [Windows](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_4_2)

```bash
export GEMINI_API_KEY="YOUR_API_KEY"
```

```bash
setx GEMINI_API_KEY "YOUR_API_KEY"
```

- [macOS / Linux](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_5_1)
- [Windows](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_5_2)

```bash
export AZURE_OPENAI_API_KEY="YOUR_API_KEY"
export AZURE_OPENAI_ENDPOINT="https://YOUR-RESOURCE.openai.azure.com/"
```

```bash
setx AZURE_OPENAI_API_KEY "YOUR_API_KEY"
setx AZURE_OPENAI_ENDPOINT "https://YOUR-RESOURCE.openai.azure.com/"
```

### Build Your First Agent Workflow

Let's build a poetic AI assistant that responds in rhymes using AG2 and your model provider of choice.

Create a Python script called `first_agent.py`, and paste the code for your provider into it. The agent behaviour is identical across providers — only the `LLMConfig` differs.

- [OpenAI](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_6_1)
- [Gemini](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_6_2)
- [Azure OpenAI](https://docs.ag2.ai/0.13.2/docs/quick-start/#__tabbed_6_3)

```python
import os

from autogen import ConversableAgent, LLMConfig

# 1. Define our LLM configuration for OpenAI's gpt-5-nano
#    uses the OPENAI_API_KEY environment variable
llm_config = LLMConfig(
    {"api_type": "openai", "model": "gpt-5-nano", "api_key": os.environ["OPENAI_API_KEY"]}
)

# 2. Create our LLM agent
my_agent = ConversableAgent(
    name="helpful_agent",
    system_message="You are a poetic AI assistant, respond in rhyme.",
    llm_config=llm_config,
)

# 3. Run the agent with a prompt and process the response
response = my_agent.run(
    message="In one sentence, what's the big deal about AI?",
    max_turns=3,
    user_input=True,
)
response.process()
```

```python
import os

from autogen import ConversableAgent, LLMConfig

# 1. Define our LLM configuration for Google Gemini
#    uses the GEMINI_API_KEY environment variable
llm_config = LLMConfig(
    {"api_type": "google", "model": "gemini-2.5-flash", "api_key": os.environ["GEMINI_API_KEY"]}
)

```python
import os

from autogen import ConversableAgent, LLMConfig

# 1. Define our LLM configuration for Azure OpenAI
#    "model" must match your Azure *deployment name*, not the underlying model name
llm_config = LLMConfig(
    {
        "api_type": "azure",
        "model": "my-gpt-deployment",
        "api_key": os.environ["AZURE_OPENAI_API_KEY"],
        "base_url": os.environ["AZURE_OPENAI_ENDPOINT"],
        "api_version": "2025-01-01",
    }
)

Why `run()` then `process()`?

`run()` prepares the conversation, `process()` executes it. This two-step pattern gives you a chance to inspect or modify the workflow before it runs.

### Run Your Example

In your terminal, run:

```bash
python first_agent.py
```

If everything is set up correctly, the agent will reply to your initial message in rhyme, then prompt you for a response. You can either:

- **Type a reply** — and the agent will respond in rhyme to your message
- **Press Enter** — to send an empty message to the agent, and see how it creatively responds
- **Type exit** — to end the conversation

The interaction continues for up to 3 turns (or until you exit).

#### Example Output

```
user (to helpful_agent):

In one sentence, what's the big deal about AI?

--------------------------------------------------------------------------------

>>>>>>>> USING AUTO REPLY...
helpful_agent (to user):

AI transforms our world, enhancing life's parade,
With insights and solutions, it helps plans cascade.

--------------------------------------------------------------------------------
Replying as user. Provide feedback to helpful_agent. Press enter to skip and use auto-reply, or type 'exit' to end the conversation:
```

Try it without installing

Want to see AG2 in action right away? The [AG2 Playground](https://playground.ag2.ai/) lets you run multi-agent workflows live in your browser — no setup required.

### What's Next?

Now that you've built your first agent, here's where to go:

- **[Overview](https://docs.ag2.ai/0.13.2/docs/user-guide/basic-concepts/overview/)** — Understand the core building blocks of AG2
- **[LLM Configuration](https://docs.ag2.ai/0.13.2/docs/user-guide/basic-concepts/llm-configuration/)** — Configure different model providers (Gemini, Anthropic, etc.)
- **[Introducing Group Chat](https://docs.ag2.ai/0.13.2/docs/user-guide/basic-concepts/introducing-group-chat/)** — Make multiple agents collaborate together

Back to top