Academy

Short guides to AI agents and AI workflows in plain words, from the first install to setups that do real work.

01 · Beginner
What is an AI agent?
You give it a goal, it works on your files until the job is done. What that looks like, what it needs from you, and how to keep it in check.
02 · Beginner
AI workflows, agent workflows and AI agents
Three ways to put AI to work, from fixed steps you design to an agent that plans on its own. What each one is, and how to pick.
03 · Beginner
Skills, connectors and plugins
The three kinds of add-on you will meet in the Library, what each one changes about your agent, and how to pick.
04 · Beginner
Install your first AI agent
Pick the agent that fits the plan you already pay for, install it from the official instructions, and try it on something you can check.
05 · Beginner
When a setup fails
Most failed installs come down to a handful of causes. What to check, in what order, and what to send when you ask for help.

Key terms

AI agent: A program that takes a goal in plain words and works towards it on its own, planning steps, using tools such as files, a terminal or the web, and checking each result (examples: Claude Code, Codex CLI, OpenCode, goose).
AI workflow: A fixed sequence of steps designed in advance in which AI does one or more of the steps, built in automation tools such as n8n, Dify, Langflow or ComfyUI.
Agent workflow (agentic workflow): A workflow with a fixed route in which some steps are handed to AI agents that can search, reason and retry within their part.
Agent skill: A folder with a SKILL.md file of instructions, and sometimes scripts, that teaches an AI agent how to do one kind of job.
MCP server (connector): A small program built on the Model Context Protocol that lets an AI agent use another app or data source, such as a browser, GitHub, Notion or a database.
Agent plugin: A ready-made pack for one specific AI agent that can bundle commands, skills, connectors and settings, installed through that agent's plugin system.