Show Notes
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
More from Today in Tech
Companies have spent billions racing to adopt artificial intelligence. But as AI moves from experimentation into production, are businesses discovering that the real costs are much higher than expected?
AI agents are moving beyond simple chatbots and isolated tasks. The next step is agent-to-agent communication, where AI systems operated by different companies could negotiate, exchange information, make decisions and even conduct business with each other.
AI was supposed to save us time. Instead, it may be creating a new problem: AI slop (polished-looking emails, reports, presentations, research and code that someone else has to review, fact-check and fix).
AI tools such as ChatGPT, Claude and Copilot are spreading rapidly through the workplace, but simply giving employees access to AI isn't the same as teaching them how to use it effectively.
Hackers are using AI, social engineering, and legitimate business tools to make cyberattacks look like normal work. Instead of breaking through security systems, they study how employees communicate, impersonate trusted vendors, manipulate email conversations, and exploit everyday business processes.