Software Architecture
7 posts on this topic — practical guidance from Shawn Livermore on fractional CTO, AI, and technology leadership.
Enterprise Software Creation in the AI Era: What Actually Changes
Karpathy's LLM Knowledge Base concept — using AI to compile and maintain institutional knowledge rather than just generate code — is the most significant architectural signal for enterprise software teams in 2026. Most organizations won't act on it until they're behind.
Read post →Vibe Coding Starter Templates: What Your First Choice Costs You
The starter template you choose when vibe coding doesn't just set up your file structure — it determines the architectural assumptions that every AI-generated file will inherit and extend. Most teams pick it in ten minutes and live with the consequences for two years.
Read post →The Vibe Coding Code Footprint: Why Your Starter Template Is a Governance Decision
How you start a vibe coding session shapes every line that follows. The starter template is not a convenience — it is the governance boundary that determines whether the code is reviewable, extensible, and safe.
Read post →The Enterprise Software Specification Is Broken. AI Is Making That Visible.
AI coding tools fill specification gaps with defaults from their training data. In enterprise software, those defaults are rarely correct. The specification problem that always existed is now impossible to ignore.
Read post →The Context File Your AI Coding Tool Needs Before the First Prompt
Starter templates set the structure of your codebase. Context files tell AI tools how to behave within it. The second matters as much as the first — and most teams skip it.
Read post →Enterprise Vibe Coding: Why Speed Without Governance Breaks at Scale
Individual AI coding assistance is a productivity story. The same capability running across 20 engineers in a shared codebase with security requirements and integration dependencies is a governance problem.
Read post →Vibe Coding Templates: What Your Codebase Leaves Behind
AI-generated code moves fast. The patterns and assumptions it deposits in your codebase stick around much longer. Here is why starter templates exist and what responsible vibe coding looks like in practice.
Read post →