← All exercises
Exercise 10

Captain's Log

You walked in as a passenger. You leave as the captain.

Duration 30–45 minutes
Difficulty All levels
Prerequisites Exercises 01–09 — the complete hands-on journey.
Captain's Log

Overview

You made it. That's not a figure of speech. There were a dozen moments across these chapters where you could have stopped — when the terminal threw an error you didn't understand, when Git asked you to resolve a merge conflict, when the deploy failed at midnight. You didn't stop. You're here.

In Chapter 1, you opened a terminal for the first time. Now you've pair-programmed with an AI agent, shipped a SaaS product, pentested it for vulnerabilities, automated a CI/CD pipeline, and read a professional security report that autonomous agents wrote for you. That's a transformation.

You can't un-learn how to read a stack trace. You can't un-see the structure behind every web application you use. The lens is permanent.

— from the exercise

By the end of this exercise

A CLAUDE.md file — your captain's orders for AI agents on your own projects
A retrospective of every skill you've built across 10 exercises
A checklist for your maiden voyage — your first solo project
A map of resources for continued learning and exploration

Terms you'll learn

Term What it means
CLAUDE.md A project-level instruction file that tells AI agents how to work on your codebase
Conventions Rules you define: coding style, commit messages, file structure
Boundaries Things the agent must not do — no refactoring to TypeScript, no build systems
Maiden voyage Your first solo project — applying everything you've learned without a guide

Sections in this exercise

01 Look Astern
02 The Ship You Built
03 One Last Exercise: Write Your Captain's Orders
04 Charts for Open Water
05 Signal Flags: A Captain's Checklist
06 The Crew is Hiring
07 The Maiden Voyage Challenge
08 Fair Winds

The ship you built

The terminal

Your helm. Navigation of file systems, running commands, piping output, reading logs.

Git and GitHub

Your logbook and harbour. Track changes, branch experiments, merge work, review code.

AI agents

Your crew. Prompt them, constrain them, read output critically, iterate.

Deployment

Your sea legs. Real servers, real domains, HTTPS, reverse proxies, DNS.

Security awareness

Your lookout. SQL injection, input sanitisation, authentication flaws.

The review habit

Your compass. Never ship without reading. Never trust output without verifying.

Charts for open water

The Agentic Crew: Theory

The companion engineering book — 19 chapters on how agents work under the hood

Anthropic Documentation

docs.anthropic.com — the official reference for Claude models and APIs

Claude Code Documentation

docs.anthropic.com/claude-code — how to get the most from your AI coding assistant

OWASP Top Ten

owasp.org — the ten most critical web application security risks

GitHub Good First Issues

Real open-source projects looking for contributors like you

OverTheWire Wargames

overthewire.org — progressive security challenges to sharpen your skills

Every effective use of AI agents comes down to one skill: writing clear instructions for a non-human collaborator. The CLAUDE.md file is the purest expression of that skill. Get good at writing these, and every agent you work with — today and in the future — gets better.