You’re Head Chef, Not A Line Cook: How Vibe Coding Changes the Developer Mindset

The following is an excerpt from the forthcoming book Vibe Coding: Building Production-Grade Software With GenAI, Chat, Agents, and Beyond by Gene Kim and Steve Yegge.

In the old days as a solitary developer, implementing a simple visualization dashboard could require any number of tedious steps: hours researching charting libraries, reading all the documentation, figuring out the configuration options, parsing data files, handling functions to throw out bad data, and implementing user interactions. Then you slowly type out code, perhaps copying and pasting code you find on the internet. When stuff goes wrong, you debug by looking at log statements and maybe stepping through with a debugger.

Yuck! How did we do this for so long?

With vibe coding, you say: “Here’s some input data. Create a chart with years on the x-axis.” Within seconds, you’ll see your chart. Then you guide your AI assistant toward what you want (e.g., “Make the y-axis logarithmic.” “Use a stacked bar chart instead.”).

In this new world, you’re the head chef of a world-class kitchen. As such, you don’t personally dice every vegetable, sear every steak, swish away every cockroach, or plate every dish. You have sous chefs and line chefs for that. But when a meal leaves the kitchen, it’s your reputation on the line and your Michelin Stars at stake. When the customer sends back the fish because it’s overdone or the sauce is broken, you can’t blame your sous chef.

The same principle applies when coding with AI: Delegation of implementation doesn’t mean delegation of responsibility. Your users, colleagues, and leadership don’t (or shouldn’t) care which parts were written by AI—they rightfully expect you to stand behind every line of code. When something breaks in production at 2 a.m., no one wants to hear, “Well, AI wrote that part.” You own the final result, period.

This is both liberating and challenging. When vibe coding, you’ll:

• Spend more time thinking about what you want to build and less time on implementation details. (Which is nice.)
• Develop a critical eye for evaluating AI-generated solutions, rather than crafting every line yourself. (Some may miss the coding part, though.)
• Learn to communicate your requirements to a non-human collaborator. (This can have a real learning curve.)
• Take responsibility for the final product while delegating much of the implementation work. (This should already be a familiar, perhaps unnerving feeling to many of you who have been in technical leadership roles. You’ll find it’s not so different with AI helpers.)

The Broader Responsibilities of a Head Chef

Coding is to home cooking, what vibe coding is to running a professional kitchen. When you don your head chef’s hat and start using coding agents, like us, you’ll notice a bunch of strange things start happening.

For over a decade, we (like most developers) have used version control systems like a glorified save button—save, undo, restore, maybe occasionally branching now and then. We mostly wrote commit messages like “fix something dumb” and pushed straight to the trunk of the code base, then rewound to an older revision if we messed something up.

But since we’ve started using coding agents, we regularly find ourselves smack in the middle of operations that we’ve previously only seen handled by release engineers and version control virtuosos. Since we both use Git, we find ourselves cherry-picking commits, merging selective changes across three or more branches, and doing complex rebases. Plus, more—way more. 

We’re using Git features that we barely know the names of, and we’re doing it a lot. But it’s not about Git. This would be happening no matter what version control system we used. We started scratching our heads over why we were doing all this complicated Git stuff every day. Was it nothing but a distraction? We soon realized that this was yet more evidence that vibe coding turns an individual into a team. We had both been using team-related Git commands that you usually only use in fast-paced teams.

It’s one thing to think of your kitchen of sous chefs as individual helpers. But no chef is an island: Teams require coordination in ways that individuals don’t. With vibe coding, you’ll be responsible for:

• Managing Parallel Development: Running multiple agents working on different tasks simultaneously, with time spans ranging from minutes to weeks—the opposite of the traditional “single-threaded” developer approach.
• Handling Complex Integration: Merging work from different branches and resolving the inevitable conflicts that arise when multiple agents modify related code.
• Setting Standards: Defining explicit coding standards and processes so your AI team operates consistently and efficiently.
• Creating Onboarding Procedures: Setting up workspaces, access, and instructions for each new AI assistant you bring into your system.
• Coordinating Larger Projects: Taking on more ambitious work than ever before, requiring you to think like a project manager.

This team stuff is all new for most solo developers and doing it with AI agents is new for everyone. But make no mistake: There is no opt-out for this “promotion” to head chef—it is inherent to vibe coding, which is how all software will soon be developed. 

For better or worse, from now on, anyone developing software who goes head-to-head against a well-managed team of AI agents without a team of their own will nearly always lose. No matter how good you are at football, if you take on an NFL team alone you will lose (unless perhaps it’s Detroit). And this competitive mismatch (outside Michigan) will drive everyone, including you, to adopt teams of AI agents. 

That makes you a team leader. Unless you still prefer to write code by hand (like a savage), you are now officially promoted to head chef. (We’ll talk a lot more about the importance of coordination in Part 4, both for individuals and for leaders.)

You may still think AI only speeds up your solo work. That was true in 2024, but with the emergence of coding agents, a broader picture is beginning to unfold. Up until now, using AI colleagues has accelerated you. But now your role is to accelerate them.

So, get ready, head chefs. We are entering a brand-new world, for sure. 

Stay tuned for more exclusive excerpts from the upcoming book Vibe Coding: Building Production-Grade Software With GenAI, Chat, Agents, and Beyond by Gene Kim and Steve Yegge on this blog or by signing up for the IT Revolution newsletter.

- About The Authors

Gene Kim

Gene Kim has been studying high-performing technology organizations since 1999. He was the founder and CTO of Tripwire, Inc., an enterprise security software company, where he served for 13 years. His books have sold over 1 million copies—he is the WSJ bestselling author of Wiring the Winning Organization, The Unicorn Project, and co-author of The Phoenix Project, The DevOps Handbook, and the Shingo Publication Award-winning Accelerate. Since 2014, he has been the organizer of DevOps Enterprise Summit (now Enterprise Technology Leadership Summit), studying the technology transformations of large, complex organizations.

Follow Gene on Social Media

• 
• 

Steve Yegge

Steve Yegge is an American computer programmer and blogger known for writing about programming languages, productivity, and software culture for two decades. He has spent over thirty years in the industry, split evenly between dev and leadership roles, including nineteen years combined at Google and Amazon. Steve has written over a million lines of production code in a dozen languages, has helped build and launch many large production systems at big tech companies, has led multiple teams of up to 150 people, and has spent much of his career relentlessly focused on making himself and other developers faster and better. He is currently an Engineer at Sourcegraph working on AI coding assistants.

Follow Steve on Social Media

•