After two greenfield cloud builds in financial services, these are the decisions that aged well, the ones I would redo, and why the small choices in year one decide whether you have a platform or a pile in year five.
The strategy posts say AI software development is a system. Here is the working loop I run inside that system: a refined specification, a layer of standards, and a coordinated set of specialists doing the work.
After thirteen months of daily Claude Code use, I stopped treating AI coding as a prompt discipline problem and started treating it like an engineering system: configurable, layered, observable, and built to learn.
Every tool in your product development life cycle is now an AI agent trying to do everything. Here is how to stop the chaos, draw the right boundaries, and build an orchestrated pipeline that actually works.
Most engineers treat AI-generated code like work from a junior developer they don't trust. Simon Willison gave me a better mental model: the dark factory. Here is what it means, why experience is the raw material, and how to build a system that runs.
Google dropped Gemma 4, and I had it running locally the same night. What open weights actually mean, the hardware reality, and why the most interesting AI architectures are about to go hybrid — on-device and in the cloud.
After thousands of sessions with Claude Code, Codex, Kiro, and every other LLM-based CLI and IDE, I distilled what I learned into a reusable Claude Skill. Here's how those lessons became the guardrails that let me move faster and actually trust the output.