Adam Bender, Principal Software Engineer at Google, argues that the AI coding debate focuses too narrowly on speed and code generation, missing the broader engineering challenges. He distinguishes programming (a single person writing code) from software engineering (keeping code alive, integrated, and maintainable over years), noting AI accelerates the former but barely touches the latter. Key concerns include: the developer ecosystem as a complex adaptive system where 10x output creates unpredictable ripple effects; the risk of losing intellectual control as codebases grow faster than human comprehension; integration testing gaps as agents flood teams with unit tests; internal APIs becoming effectively public when agents ignore informal boundaries; and the challenge of teaching engineering judgment to new developers who have agents but no instinct. Bender recommends starting by defining what quality means for your business, then mapping your full developer ecosystem to anticipate second- and third-order consequences of dramatically increased code output.
Table of contents
Get oriented on a big PR before you review it (Sponsored)1. Most of the conversation about AI and coding is about speed. When someone only asks whether the AI writes good code, what are they not seeing?2. You said, “engineering is programming integrated over time”. AI is speeding up the programming part, but why doesn’t that speed up the engineering part too?3. Half of your book is about culture, not code. Why can’t anyone copy Google’s technical choices without first understanding the culture?4. In your talk, you use Conway’s Law as the door into everything else. Now that agents write and change code, do they become part of that shape too?5. One of the most interesting things you said is that all your internal APIs just became public, because an agent won’t respect a boundary you only ever enforced with good manners. Where should a team start hardening?6. If no one is writing the code, a year from now, who is actually watching the codebase as it grows?7. You wrote the testing chapters in the book, and yet on stage you admitted you don’t have the integration testing tools you want. When output increases 10x, which part of testing breaks first?8. You said the thing keeping you up at night is intellectual control, whether a human can still reason about the system in front of them. Is AI making it worse?9. How do you teach someone ten years of judgment in six months, when they have fifty agents and none of the instinct yet? Have you seen anything that even partly works?10. You ended by telling the room they have more agency than they think. For an engineer who cares about quality and feels carried along by all of this, where do they actually start on Monday morning?Want to advertise in Tech World With Milan? 📰Love Tech World With Milan Newsletter? Tell your friends and get rewards.78.9K Impressions2 Comments