Free online guide · 14 chapters

Working With AI Agents

A practical guide for non-technical people who want to understand and use AI coding agents to build real things.

What you'll learn

No coding background required. Go from zero understanding to confidently directing an AI agent through a real project.

Chapter 1

What AI Agents Are (and Aren't)

What AI agents are, how to direct them, and what engines power them.

Chapter 2

Memory and Context

Context windows, what gets lost between sessions, and external memory layers.

Chapter 3

Tools of the Trade

Three ways to work with AI: chat, platform, or agent-assisted tools.

Chapter 4

Setting Up

Installing Claude Code, configuring VS Code, and running your first command.

Chapter 5

Git and GitHub

Saving your work, going back to previous versions, and backing up online.

Chapter 6

Configuring Your Agent

Instruction files, rules, memory, custom agents, and MCP servers.

Chapter 7

The Meta-Process

The recommended structure for agent work: orchestrator, explorer, actor, reviewer, iterate.

Chapter 8

Content Writing Example

The meta-process in action: a flag blog with two agents, two skills, and one command. Full build walkthrough.

Chapter 9

Writing Effective Instructions

The craft of writing instruction files that actually work.

Chapter 10

OpenClaw

OpenClaw and the world of personal AI agents — what they do, how they work, and what can go wrong.

Chapter 11

Building Software with Agents

The same process at scale — multiple agents building a software feature.

Chapter 12

Claude Built-in Capabilities

Built-in slash commands, tools, and capabilities that ship with Claude Code.

Chapter 13

Roy's Claude Config

A real Claude Code setup: agents, commands, rules, and links to other public configs.

Chapter 14

Servers, Hosting, and Deployment

Where your project lives and how people access it after you build it.

Ready to get started?

The guide is free, takes about an hour to read, and will change how you think about building with AI.

Contact Me