Vibe coding has gone from “kicking the tires” to shipping real software—but what does AI-powered vibe coding break along the way? In this episode of Today in Tech, Keith Shaw sits down with Scott Breitenother, CEO and co-founder of Kilo Code, to unpack how AI-assisted development is changing the craft of programming—and the structure of engineering teams.

Scott explains what vibe coding really means, why “one-shot” prompts often fail, and how the best teams are already using multiple AI agents to build and review features. We also dig into the big questions leaders are wrestling with right now: how to create guardrails and quality gates, what happens to junior developer pipelines, and whether AI will reduce or multiply tech debt as more people build more software faster.

Topics covered:

What “vibe coding” is (and why the name may disappear)

Why specificity beats “magic prompts”

AI as a multiplier: vision + architecture still matter

Quality gates: AI code review + human review

Team redesign: one engineer managing multiple agents

Tech debt, maintenance, and the “slop” problem

How education and career paths will change