You're Not a 10x Developer. You're Just Typing Less.
Explore the intersection of software craftsmanship and artificial intelligence with Founder of Plushcap and Creator of Full Stack Python, Matthew Makai. This episode examines the reality of using agentic tools in production and why maintaining your architectural foundation is a critical defense against technical debt. Learn how to stay ahead of market trends while preserving the expertise that makes a great engineer.
Join software developer and educator Matthew Makai for an in-depth exploration of the rapidly shifting landscape of AI-powered engineering. This conversation traces Matt's transition from creating Full Stack Python to founding Plushcap, where he currently tracks hundreds of emerging AI coding tools and identifies market trends before they explode.
We explore the critical distinction between essential and accidental complexity and why the "read-only-first" planning phase is vital for preventing AI-induced technical debt. Matt shares his personal tandem workflow for using agentic systems to both generate and review code, emphasizing that technical credibility remains the ultimate guardrail against automated errors.
The discussion also critiques the financial motivations behind current industry marketing and why the narrative of software engineers being replaced by AI is often driven by seat-based licensing models rather than technical reality. By looking back at the history of software development, from the invention of COBOL to the rise of web frameworks, the guest and hosts outline why curiosity and architectural rigor are the most important attributes for engineers in 2026 and beyond.
Key Takeaways
- The human in the loop still matters. Agentic tools amplify your architecture, good or bad, so engineering judgment doesn't go away
- Adding a review step to your AI coding workflow (like running codex review alongside Claude Code) can dramatically reduce bugs reaching production
- Essential complexity doesn't disappear with AI. Understanding what you're building remains the developer's job
- Teams with strong technical foundations before AI tools are best positioned to benefit from them without the downsides
- Skepticism is a skill — a lot of the doom and hype around AI replacing developers is marketing, not signal
- Qodo's context-aware code review with rules as guardrails is how engineering teams turn AI productivity into production-ready quality
Episode resources