This guide is for people who aren't developers but want to understand — and use — AI agents to build things. No coding background required. By the end, you'll know what agents are, how they think (and don't), what tools exist, and how to direct an agent through a real project.
Here's what each chapter covers:
- What AI Agents Are (and Aren't) — What AI agents are, how to direct them, and what engines (models) power them. Agents are eager, literal workers. Your job is to brief clearly and set boundaries.
- Memory and Context — Agents have no long-term memory. This chapter explains context windows, what gets lost between sessions, and the three layers of external memory you'll need to understand.
- Tools of the Trade — There are three ways to work with AI: chat with it directly, use an all-in-one platform, or use an agent-assisted tool. This chapter maps the landscape and helps you pick.
- Setting Up — Installing Claude Code, configuring VS Code, and running your first command. Step by step.
- Configuring Your Agent — The instruction file (CLAUDE.md), rules, memory, custom agents, skills, hooks, and MCP servers. How to set up your agent's working environment before you start building.
- Your First Project — A hands-on walkthrough: from blank folder to working website.
- Git and GitHub — Version control: saving your work, going back to previous versions, and backing up your project online.
- Servers, Hosting, and Deployment — What happens after you build something. Where it lives, how people access it.
Each chapter ends with a Practical tips section — short, concrete advice you can apply immediately. You don't need to read those tips upfront. They're there when you need them.
Glossary — Every technical term introduced in this guide, collected in one place. Not a chapter — an addendum you can flip to anytime.