# Conversable Agent

ConversableAgent is at the heart of all AG2 agents while also being a fully functioning agent.

Let's _converse_ with ConversableAgent in just 5 simple steps.

```javascript
import Example from "/snippets/python-examples/conversableagentchat.mdx";
```

Let's break it down:

1. Import `ConversableAgent`, you'll find the most popular classes available directly from `autogen`.
2. Create our LLM configuration to define the LLM that our agent will use.
3. Create our ConversableAgent, give them a unique name, and use `system_message` to define their purpose.
4. Ask the agent a question using their `run` method, passing in our starting message.

```
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 with endless potential, enhancing lives and knowledge, truly essential.
   --------------------------------------------------------------------------------
Replying as user. Provide feedback to helpful_agent. Press enter to skip and use auto-reply, or type 'exit' to end the conversation:
```