AI Product Management

Chapter 2. Rapid Prototyping and Iteration with AI

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 4th 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].

“The best way to predict the future is to invent it.”

Alan Kay

In traditional software development, the distance between an idea and a working product is measured in weeks or months. In the era of AI engineering, it is measured in minutes.

Ironically, time estimates for coding agents are notoriously incorrect. This is because large language models (LLMs) are trained on data from humans. To get a feel for this, try this prompt out for yourself after asking a coding agent to scope a new feature: “How long do you think this will take?”. Most likely, the agent will respond in very human terms, by saying things like “this feature will take one or two engineering sprints to complete, which is around four weeks of work…”, even though when you ask the agent to implement the same feature, it will complete it in less than a few minutes!

This shift in velocity fundamentally changes the role of a PM. When the cost of building falls to near zero, the ...