vibecoding Archives - Scrum Master Toolbox Podcast

AI Assisted Coding: Treating AI Like a Junior Engineer – Onboarding Practices for AI Collaboration

In this special episode, Sergey Sergyenko, CEO of Cybergizer, shares his practical framework for AI-assisted development built on transactional models, Git workflows, and architectural conventions. He explains why treating AI like a junior engineer, keeping commits atomic, and maintaining rollback strategies creates production-ready code rather than just prototypes.

Vibecoding: An Automation Design Instrument

“I would define Vibecoding as an automation design instrument. It’s not a tool that can deliver end-to-end solution, but it’s like a perfect set of helping hands for a person who knows what they need to do.”

Sergey positions vibecoding clearly: it’s not magic, it’s an automation design tool. The person using it must know what they need to accomplish—AI provides the helping hands to execute that vision faster. This framing sets expectations appropriately: AI speeds up development significantly, but it’s not a silver bullet that works without guidance. The more you practice vibecoding, the better you understand its boundaries. Sergey’s definition places vibecoding in the evolution of development tools: from scaffolding to co-pilots to agentic coding to vibecoding. Each step increases automation, but the human architect remains essential for providing direction, context, and validation.

Pair Programming with the Machine

“If you treat AI as a junior engineer, it’s very easy to adopt it. Ah, okay, maybe we just use the old traditions, how we onboard juniors to the team, and let AI follow this step.”

One of Sergey’s most practical insights is treating AI like a junior engineer joining your team. This mental model immediately clarifies roles and expectations. You wouldn’t let a junior architect your system or write all your tests—so why let AI? Instead, apply existing onboarding practices: pair programming, code reviews, test-driven development, architectural guidance. This approach leverages Extreme Programming practices that have worked for decades. The junior engineer analogy helps teams understand that AI needs mentorship, clear requirements, and frequent validation. Just as you’d provide a junior with frameworks and conventions to follow, you constrain AI with established architectural patterns and framework conventions like Ruby on Rails.

The Transactional Model: Atomic Commits and Rollback

“When you’re working with AI, the more atomic commits it delivers, more easy for you to kind of guide and navigate it through the process of development.” Continue reading AI Assisted Coding: Treating AI Like a Junior Engineer – Onboarding Practices for AI Collaboration

AI Assisted Coding: Augmented AI Development – Software Engineering First, AI Second

In this special episode, Dawid Dahl introduces Augmented AI Development (AAID)—a disciplined approach where professional developers augment their capabilities with AI while maintaining full architectural control. He explains why starting with software engineering fundamentals and adding AI where appropriate is the opposite of most frameworks, and why this approach produces production-grade software rather than technical debt.

The AAID Philosophy: Don’t Abandon Your Brain

“Two of the fundamental developer principles for AAID are: first, don’t abandon your brain. And the second is incremental steps.”

Dawid’s Augmented AI Development framework stands in stark contrast to “vibecoding“—which he defines strictly as not caring about code at all, only results on screen. AAID is explicitly designed for professional developers who maintain full understanding and control of their systems. The framework is positioned on the furthest end of the spectrum from vibe coding, requiring developers to know their craft deeply. The two core principles—don’t abandon your brain, work incrementally—reflect a philosophy that AI is a powerful collaborator, not a replacement for thinking. This approach recognizes that while 96% of Dawid’s code is now written by AI, he remains the architect, constantly steering and verifying every step.

In this segment we refer to Marcus Hammarberg’s work and his book The Bungsu Story.

Software Engineering First, AI Second: A Hill to Die On

“You should start with software engineering wisdom, and then only add AI where it’s actually appropriate. I think this is super, super important, and the entire foundation of this framework. This is a hill I will personally die on.”

What makes AAID fundamentally different from other AI-assisted development frameworks is its starting point. Most frameworks start with AI capabilities and try to add structure and best practices afterward. Dawid argues this is completely backwards. AAID begins with 50-60 years of proven software engineering wisdom—test-driven development, behavior-driven development, continuous delivery—and only then adds AI where it enhances the process. This isn’t a minor philosophical difference; it’s the foundation of producing maintainable, production-grade software. Dawid admits he’s sometimes “manipulating developers to start using good, normal software engineering practices, but in this shiny AI box that feels very exciting and new.” If the AI wrapper helps developers finally adopt TDD and BDD, he’s fine with that.

Why TDD is Non-Negotiable with AI

“Every time I prompt an AI and it writes code for me, there is often at least one or two or three mistakes that will cause catastrophic mistakes down the line and make the software impossible to change.” Continue reading AI Assisted Coding: Augmented AI Development – Software Engineering First, AI Second

AI Assisted Coding: Swimming in AI – Managing Tech Debt in the Age of AI-Assisted Coding

In this special episode, Lou Franco, veteran software engineer and author of “Swimming in Tech Debt,” shares his practical approach to AI-assisted coding that produces the same amount of tech debt as traditional development—by reading every line of code. He explains the critical difference between vibecoding and AI-assisted coding, why commit-by-commit thinking matters, and how to reinvest productivity gains into code quality.

Vibecoding vs. AI-Assisted Coding: Reading Code Matters

“I read all the code that it outputs, so I need smaller steps of changes.”

Lou draws a clear distinction between vibecoding and his approach to AI-assisted coding. Vibecoding, in his definition, means not reading the code at all—just prompting, checking outputs, and prompting again. His method is fundamentally different: he reads every line of generated code before committing it. This isn’t just about catching bugs; it’s about maintaining architectural control and accountability. As Lou emphasizes, “A computer can’t be held accountable, so a computer can never make decisions. A human always has to make decisions.” This philosophy shapes his entire workflow—AI generates code quickly, but humans make the final call on what enters the repository. The distinction matters because it determines whether you’re managing tech debt proactively or discovering it later when changes become difficult.

The Moment of Shift: Staying in the Zone

“It kept me in the zone. It saved so much time! Never having to look up what a function’s arguments were… it just saved so much time.”

Lou’s AI coding journey began in late 2022 with GitHub Copilot‘s free trial. He bought a subscription immediately after the trial ended because of one transformative benefit: staying in the flow state. The autocomplete functionality eliminated constant context switching to documentation, Stack Overflow searches, and function signature lookups. This wasn’t about replacing thinking—it was about removing friction from implementation. Lou could maintain focus on the problem he was solving rather than getting derailed by syntax details. This experience shaped his understanding that AI’s value lies in removing obstacles to productivity, not in replacing the developer’s judgment about architecture and design.

Thinking in Commits: The Right Size for AI Work

“I think of prompts commit-by-commit. That’s the size of the work I’m trying to do in a prompt.” Continue reading AI Assisted Coding: Swimming in AI – Managing Tech Debt in the Age of AI-Assisted Coding

AI Assisted Coding: From Designer to Solo Developer – Building Production Apps with AI

In this special episode, Elina Patjas shares her remarkable journey from designer to solo developer, building LexieLearn—an AI-powered study tool with 1,500+ users and paying customers—entirely through AI-assisted coding. She reveals the practical workflow, anti-patterns to avoid, and why the future of software might not need permanent apps at all.

The Two-Week Transformation: From Idea to App Store

“I did that, and I launched it to App Store, and I was like, okay, so… If I can do THIS! So, what else can I do? And this all happened within 2 weeks.”

Elina’s transformation happened fast. As a designer frustrated with traditional software development where maybe 10% of your original vision gets executed, she discovered Cursor and everything changed. Within two weeks, she went from her first AI-assisted experiment to launching a complete app in the App Store. The moment that shifted everything was realizing that AI had fundamentally changed the paradigm from “writing code” to “building the product.” This wasn’t about learning to code—it was about finally being able to execute her vision 100% the way she wanted it, with immediate feedback through testing.

Building LexieLearn: Solving Real Problems for Real Users

“I got this request from a girl who was studying, and she said she would really appreciate to be able to iterate the study set… and I thought: “That’s a brilliant idea! And I can execute that!” And the next morning, it was 9.15, I sent her a screen capture.”

Lexie emerged from Elina’s frustration with ineffective study routines and gamified edtech that didn’t actually help kids learn. She built an AI-powered study tool for kids aged 10-15 that turns handwritten notes into adaptive quizzes revealing knowledge gaps—private, ad-free, and subscription-based. What makes Lexie remarkable isn’t just the technology, but the speed of iteration. When a user requested a feature, Elina designed and implemented it overnight, sending a screen capture by 9:15 AM the next morning. This kind of responsiveness—from customer feedback to working feature in hours—represents a fundamental shift in how software can be built. Today, Lexie has over 1,500 users with paying customers, proving that AI-assisted development isn’t just for prototypes anymore.

The Workflow: It’s Not Just “Vibing”

“I spend 30 minutes designing the whole workflow inside my head… all the UX interactions, the data flow, and the overall architectural decisions… so I spent a lot of time writing a really, really good spec. And then I gave that to Claude Code.” Continue reading AI Assisted Coding: From Designer to Solo Developer – Building Production Apps with AI

AI Assisted Coding: From Deterministic to AI-Driven—The New Paradigm of Software Development, With Markus Hjort

In this BONUS episode, we dive deep into the emerging world of AI-assisted coding with Markus Hjort, CTO of Bitmagic. Markus shares his hands-on experience with what’s being called “vibe coding” – a paradigm shift where developers work more like technical product owners, guiding AI agents to produce code while focusing on architecture, design patterns, and overall system quality. This conversation explores not just the tools, but the fundamental changes in how we approach software engineering as a team sport.

Defining Vibecoding: More Than Just Autocomplete

“I’m specifying the features by prompting, using different kinds of agentic tools. And the agent is producing the code. I will check how it works and glance at the code, but I’m a really technical product owner.”

Vibecoding represents a spectrum of AI-assisted development approaches. Markus positions himself between pure “vibecoding” (where developers don’t look at code at all) and traditional coding. He produces about 90% of his code using AI tools, but maintains technical oversight by reviewing architectural patterns and design decisions. The key difference from traditional autocomplete tools is the shift from deterministic programming languages to non-deterministic natural language prompting, which requires an entirely different way of thinking about software development.

The Paradigm Shift: When AI Changed Everything

“It’s a different paradigm! Looking back, it started with autocomplete where Copilot could implement simple functions. But the real change came with agentic coding tools like Cursor and Claude Code.”

Markus traces his journey through three distinct phases. First came GitHub Copilot‘s autocomplete features for simple functions – helpful but limited. Next, ChatGPT enabled discussing architectural problems and getting code suggestions for unfamiliar technologies. The breakthrough arrived with agentic tools like Cursor and Claude Code that can autonomously implement entire features. This progression mirrors the historical shift from assembly to high-level languages, but with a crucial difference: the move from deterministic to non-deterministic communication with machines.

Where Vibecoding Works Best: Knowing Your Risks

“I move between different levels as I go through different tasks. In areas like CSS styling where I’m not very professional, I trust the AI more. But in core architecture where quality matters most, I look more thoroughly.” Continue reading AI Assisted Coding: From Deterministic to AI-Driven—The New Paradigm of Software Development, With Markus Hjort