Claude Code: Up and Running

Chapter 1. The Rise of Agentic Development

You’re not a Java developer or a JavaScript developer or a Python developer. You’re a developer.

Venkat Subramaniam

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the 1st chapter of the final book. The GitHub repo is active.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

Agentic coding tools blur boundaries that used to feel solid: language, framework, domain, repository, even role. When a capable agent can work inside your project, the bottleneck is no longer typing every line of code. The harder problem is directing the work: naming the outcome, setting the success conditions, checking the result, and deciding when the first answer is not good enough.

That shift requires a deliberate practice, increasingly called agentic development: the agent drives the implementation, and you drive the direction, verification, and judgment. What this book adds is the project-scale progression — doghouse to cabin to skyscraper — that shows how the practice changes as the stakes grow.

In practice, Claude Code looks ordinary at first: you open a terminal in a project directory, type a request, watch it inspect files and propose actions, approve or reject ...