Scaling AI Adoption in Engineering

Chapter 4. Building Personal Competence

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].

In late 2025, I was talking with Bob Matsuoka, former VP of Engineering at TripAdvisor. He’d taken a break from running large engineering orgs to figure out what LLMs could do. He’d built up substantial experience building and operating agentic software factories (systems where agents write, verify, and deploy code, without necessarily requiring human review or approval).

I had all kinds of questions about how to build an orchestrator for running my own agents and an agent-first system of record for Gather.dev (my CTO-community business), but it turned out that what I really needed was to revisit my assumptions.

For example, when I asked detailed questions about how to build the UX for the apps, Bob simply said, “You might not need a UX. Just ask the agents for the information you need.”

Building with LLMs is fundamentally counterintuitive, and I didn’t really get it until I stopped researching and started prompting iteratively toward the systems I wanted ...