Quickstart

Get AEL running in 5 minutes.

Prerequisites

• AEL installed (Installation Guide)
• Terminal access

Step 1: Create Project Directory

mkdir my-ael-project
cd my-ael-project

Step 2: Create Configuration

Create ael-config.yaml:

workflows:
  directory: "./workflows"

logging:
  level: INFO

Step 3: Create Your First Workflow

Create workflows/hello.yaml:

name: hello
version: "1.0"
description: A simple hello world workflow

inputs:
  name:
    type: string
    default: "World"

steps:
  - id: greet
    code: |
      name = "{{ inputs.name }}"
      result = f"Hello, {name}!"

output: "{{ steps.greet.output }}"

Step 4: Validate the Workflow

ael validate workflows/hello.yaml

Expected output:

✓ Workflow 'hello' is valid

Step 5: Run the Workflow

ael run workflows/hello.yaml

Expected output:

Hello, World!

Run with custom input:

ael run workflows/hello.yaml -i name=Alice

Expected output:

Hello, Alice!

Step 6: Start as MCP Server (Optional)

Start AEL as an MCP server for AI agent integration:

ael serve

The workflow is now available as an MCP tool named workflow:hello.

What's Next?

You've successfully: - ✅ Created an AEL project - ✅ Written a workflow - ✅ Validated and executed it - ✅ Started AEL as an MCP server

Continue Learning

• First Workflow Tutorial - Build a more complex workflow
• Workflow Authoring Guide - Deep dive into workflows
• CLI Reference - All available commands

Try More Examples

• Web Scraping Example
• Data Processing Example
• API Integration Example