I’m entering the final stretch on my second book, Claude Code Beyond the Prompt.
Over the next few weeks, I’ll share the ideas that are the foundation of agentic engineering and that are covered in the 14 Chapters of Claude Code Beyond the Prompt.
When I wrote my first book, The Complete Developer No Starch Press, I wanted to explain how the parts of modern web development fit together. Because knowing one aspect in isolation is never enough.
When Packt approached me about writing a book on Claude Code and Agent Skills, I kept running into the same problem: Knowing how to write a good prompt is genuinely useful. But it is not enough.
A good prompt can solve the problem in front of you. But what happens when the same kind of work comes up again tomorrow? What happens when another developer needs to follow the same method? Or when Claude needs to inspect a repository, run tests, read logs, use tools, or retrieve information from another system? At that point, the prompt is still important, but it is only one part of the work.
That became the subject of Claude Code Beyond the Prompt. The book starts with simple, one-off prompts and gradually builds from there: reusable skills, workflows, agents, tools, connected systems, and finally a small AI workbench.
If you’re trying to move from useful AI experiments to repeatable engineering practice, this book is for you.
Pre-Order Claude Code Beyond the Prompt (ISBN 978-1-80778-229-0) at Claude Code Beyond the Prompt or Amazon
Top comments (0)