How to separate 'what I learned about the code' from 'what I learned about working with this person' so the AI gets better across projects.

Why I stopped putting AI config files in every repo and moved project orchestration into a centralized registry instead.

Why I stopped treating AI system prompts as per-project config files and started treating them as portable operating systems.

Engineering the 48x Velocity Increase: 9-Pass Recursive Pipelines and Axiomatic Outlier Extraction.

Architecting Steerability and Observability in Long-Horizon AI Systems.

Code is a layered history of decisions. Understanding those layers is the difference between fixing symptoms and fixing systems.

How separating AI session state from your code repository into a dedicated registry follows the Unix philosophy and makes everything easier to debug.

The shift from generating one-off code snippets to building persistent, registry-backed systems that maintain state across sessions.

When you have multiple AI tools running different kernels, you need a shared logic layer. MCP turned out to be a decent fit for centralizing audit logic across Gemini CLI and Pi Agent.

A technical deep-dive into the Gemini CLI's hook system — how it works, what you can intercept, and how I use it to build guardrails for autonomous agents.

Why giving an AI agent one tool that does ten things leads to drift. Atomic, single-purpose tools are more reliable.

Running the Soul OS architecture through a 7-step agent lifecycle audit. Where it's strong, and where the gaps are.

How using multiple models to cross-check documentation prevents AI-generated hallucinations from becoming permanent.

When an AI agent gets deep into a long session, string-based safety checks start to fail. The real guardrails need to live in the execution layer, not the prompt.

When coding agents make execution cheap, the traditional Engineering-Product-Design waterfall collapses. The new bottleneck is review, not implementation.