Learning AI-Native Software Engineering

Chapter 7. SDD Frameworks Compared

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 8th chapter of the final book. Please note that the GitHub repo will be made active later on.

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

Chapter 6 walked through the Specify, Plan, Execute, Verify, Integrate, Learn loop and the artifacts that hold it together. That loop isn’t tied to any particular tool: You can run it with a plain text file and a coding agent, and many teams do. But as soon as more than one person is involved, or the same kind of spec gets written ten times, certain questions come up repeatedly: What does our spec look like? Where do we put it? Which slash command does each engineer run? When does the agent stop and ask for help?

This chapter is about the frameworks that try to answer those questions for you. There is a growing ecosystem of SDD frameworks, each with its own conventions, file layouts, and command vocabularies. Some are lightweight and fit in a few Markdown files; others ship a small team of specialized agents, with formal handoffs between them. They all agree that specifications come before code. They disagree on how much process to wrap around that idea.

The ...