Today
44m 17s
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.
"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.
"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.
"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."
Vibecoding effectiveness varies dramatically by context. Markus applies different levels of scrutiny based on his expertise and the criticality of the code. For frontend work and styling where he has less expertise, he relies more heavily on AI output and visual verification. For backend architecture and core system components, he maintains closer oversight. This risk-aware approach is essential for startup environments where developers must wear multiple hats. The beauty of this flexibility is that AI enables developers to contribute meaningfully across domains while maintaining appropriate caution in critical areas.
"You first teach your tool to do the things you value. Setting system prompts with information about patterns you want, testing approaches you prefer, and integration methods you use."
Success with AI-assisted coding requires intentional configuration and practice. Key strategies include:
System prompts: Configure tools with your preferred patterns, testing approaches, and architectural decisions
Context management: Watch context length carefully; when the AI starts making mistakes, reset the conversation
Checkpoint discipline: Commit working code frequently to Git - at least every 30 minutes, ideally after every small working feature
Dual AI strategy: Use ChatGPT or Claude for architectural discussions, then bring those ideas to coding tools for implementation
Iteration limits: Stop and reassess after roughly 5 failed iterations rather than letting AI continue indefinitely
Small steps: Split features into minimal increments and commit each piece separately
In this segment we refer to the episode with Alan Cyment on AI Assisted Coding, and the Pachinko coding anti-pattern.
"The speed changes a lot of things. If everything goes well, you can produce so much more stuff. So you have to have bigger tasks. Coordination changes - we need bigger chunks because of how much faster coding is."
AI-assisted coding fundamentally reshapes team workflows. The dramatic increase in coding speed means developers need larger, more substantial tasks to maintain flow and maximize productivity. Traditional approaches of splitting stories into tiny tasks become counterproductive when implementation speed increases 5-10x. This shift impacts planning, requiring teams to think in terms of complete features rather than granular technical tasks. The coordination challenge becomes managing handoffs and integration points when individuals can ship significant functionality in hours rather than days.
"When you're moving from low-level language to higher-level language, they are still deterministic. But now with LLMs, it's not deterministic. This changes how we have to think about coding completely."
The shift to natural language prompting introduces fundamental uncertainty absent from traditional programming. Unlike the progression from assembly to C to Python - all deterministic - working with LLMs means accepting probabilistic outputs. This requires developers to adopt new mental models: thinking in terms of guidance rather than precise instructions, maintaining checkpoints for rollback, and developing intuition for when AI is "hallucinating" versus producing valid solutions. Some developers struggle with this loss of control, while others find liberation in focusing on what to build rather than how to build it.
"With AI, I spend more time on the actual product doing exploratory testing. The AI is doing the coding, so I can focus on whether it works as intended rather than syntax and patterns."
Traditional code review loses relevance when AI generates syntactically correct, pattern-compliant code. The focus shifts to testing actual functionality and user experience. Markus emphasizes:
Manual exploratory testing becomes more important as developers can't rely on having written and understood every line
Test discipline is critical - AI can write tests that always pass (assert true), so verification is essential
Test-first approach helps ensure tests actually verify behavior rather than just existing
Periodic test validation: Randomly modify test outputs to verify they fail when they should
Loosening review processes to avoid bottlenecks when code generation accelerates dramatically
Several common mistakes emerge when developers start with AI-assisted coding:
Continuing too long: When AI makes 5+ iterations without progress, stop and reset rather than letting it spiral
Skipping commits: Without frequent Git checkpoints, recovery from AI mistakes becomes extremely difficult
Over-reliance without verification: Trusting AI-generated tests without confirming they actually test something meaningful
Ignoring context limits: Continuing to add context until the AI becomes confused and produces poor results
Maintaining traditional task sizes: Splitting work too granularly when AI enables completing larger chunks
Forgetting exploration: Reading about tools rather than experimenting hands-on with your own projects
"I hope that these LLMs will become larger context windows and smarter. Tools like Replit are pushing boundaries - they can potentially do automatic testing and verification for you."
Markus sees rapid evolution toward more autonomous development agents. Current trends include:
Expanded context windows enabling AI to understand entire codebases without manual context curation
Automatic testing generation where AI not only writes code but also creates and runs comprehensive test suites
Self-verification loops where agents test their own work and iterate without human intervention
Design-to-implementation pipelines where UI mockups directly generate working code
Agentic tools that can break down complex features autonomously and implement them incrementally
The key insight: we're moving from "AI helps me code" to "AI codes while I guide and verify" - a fundamental shift in the developer's role from implementer to architect and quality assurance.
"I haven't found a single resource that covers everything. My recommendation is to try Claude Code or Cursor yourself with your own small projects. You don't know the experience until you try it."
Rather than pointing to comprehensive guides (which don't yet exist for this rapidly evolving field), Markus advocates hands-on experimentation. Start with personal projects where stakes are low. Try multiple tools to understand their strengths. Build intuition through practice rather than theory. The field changes so rapidly that reading about tools quickly becomes outdated - but developing the mindset and practices for working with AI assistance provides durable value regardless of which specific tools dominate in the future.
About Markus Hjort
Markus is Co-founder and CTO of Bitmagic, and has over 20 years of software development expertise. Starting with Commodore 64 game programming, his career spans gaming, fintech, and more. As a programmer, consultant, agile coach, and leader, Markus has successfully guided numerous tech startups from concept to launch.
You can connect with Markus Hjort on LinkedIn.