When implementation becomes cheap, what's left? I stopped writing code, ventured into machine learning and 3D game development, and discovered that AI made me remarkably efficient at making mistakes. Fortunately, it also made me much faster at learning from them.
A startup ran out of runway and handled the layoff badly. The engineer found out from his broker. The argument here is that the company's real output was never the platform, it was the engineers it built, and no month of handover meetings can transfer that.
Two agents implemented and reviewed a full architecture refactor across five iterations, with zero lines of production code written by hand. What neither agent caught was four innocent lines in a coordinator that had quietly started making policy decisions.
Codex got the same god class Claude had failed to remove, plus one thing Claude never had: a target architecture. An implementing agent and an independent reviewer then took three rounds to converge, because agents renovate around bad architecture rather than delete it.
Handing an AI your engineering conventions cleans up the code without fixing the architecture. A 5,000-line god class shrank to 500 lines across tidy domain files, and an independent reviewing agent still returned FAIL: authority never left the central object.
Hitting a wall with AI usually means hitting the wall of the chat box, not the wall of AI itself. Give a model memory, tool access and a browser, and the interfaces we built for humans become the integration. The bottleneck stops being the model and starts being your imagination.
Auditing data-heavy companies reveals the same pattern: asynchronous data processing crammed into the synchronous web stack. The contention shows in performance, delivery, and team dynamics. Isolation fixes all three.
Business users love Lovable. Engineers tend to panic. A real-world case study of how to wrap an AI builder in guardrails so non-technical teams can move fast without quietly rewriting the systems that give your product its edge.
AI removes bottlenecks until it reaches the one that doesn’t move: human cognition. The faster AI makes your system, the more your team’s mental capacity becomes the constraint. You can’t add more of it.
The machines aren't replacing developers, they're promoting them. You're no longer just writing code; you're managing agents, reviewing output, and setting standards. Three Claudes walk into a codebase, and suddenly you're a manager.
Part 2 of the article about Mossie, when it was faced with scaling to include every bird in the world, complete with photos, sounds, and icons.
A small birding app with 300 manually entered species faced an ambitious challenge: scale to include every bird in the world, complete with photos, sounds, and icons. This article explores how the team used GenAI to bootstrap a comprehensive birding database from scratch.
Early-stage startups want full-stack unicorns who can do it all on a tight budget, but asking one dev to wear every hat is less strategic hiring and more duct-taping a rocket and hoping for the best.
In the first of a series exploring infrastructure fundamentals, Brenden addresses the most frequently asked questions about what's really happening under the hood with complex pipelines and AI/data systems, bringing the cloud to life.
Offboarding is a crucial part of security. Forgotten accounts and overlooked credentials can expose your systems to risk. This post offers real examples, a checklist approach, and clear steps to make offboarding more reliable across teams.
