Your first workflow

What you will do

Set up an n8n workspace and build a simple AI agent that responds to chat messages.

Sign up

Go to n8n.io and start a free cloud trial. The cloud service is the easiest way to get started. (Self-hosting is covered in lesson 5.)

Once you are in the workspace, you will see a blank canvas. This is where you build workflows by connecting nodes.

Understand nodes

n8n workflows are made of nodes. Each node does one thing: trigger the workflow, process data, call an API, send a message, or make a decision. You connect nodes by dragging a line from one to the next.

Every workflow needs a trigger node. The trigger tells the workflow when to start.

Build your first AI agent

1. Click Add first step or press N to open the node menu.
2. Search for Chat Trigger and add it to the canvas. This node gives you a chat interface to talk to the agent.
3. Click the + connector on the Chat Trigger node. Search for AI Agent and add it. The AI Agent node is the core node for building agents in n8n.
4. The AI Agent node needs a language model. Click the + under Chat Model on the AI Agent node. Search for OpenAI Chat Model (or Google Gemini, Anthropic, or whichever model you have credentials for).
5. Select the model node. Click the Credential dropdown and select Create New Credential. Paste your API key and save.
6. Back on the AI Agent node, you can customise the System Message. This is the prompt that tells the agent how to behave.

Example system message:

You are a helpful assistant that answers questions concisely. If you do not know the answer, say so. Do not make up information.

Test it

Click Save, then click the Chat button on the Chat Trigger node to open the chat window. Type a message. The workflow runs through the Chat Trigger, into the AI Agent node, which sends your message to the model and returns the response.

What you should see

A working chat agent on the canvas. You type a message, the AI Agent node processes it, and a response appears in the chat window.