$ ls -t posts/
-
🏗️☕🤖 The Internal Agent Platform: One Roastery, Many Cafés
Ever feel like you’re drowning in a sea of “point solutions”? One day it’s a Slack bot for checking logs, the next it’s a CLI tool for linting, and by Thursday you’ve got three different “AI assistants” that all give different advice on the same bloody …Read more → -
☕️🚀 Beyond the Prompt: The Evolution of Context Engineering in 2026
Lately, I’ve been having a lot of conversations with customers about how to shape their GEMINI.md files to get the absolute most out of the Gemini CLI. It’s a topic I’ve been giving a proper amount of thought to, and I figured it was about time I put some of those thoughts down on paper. Picture …Read more → -
🦸💻☕ The Agentic SRE: Decoupling Cognitive Load with Gemini CLI
It’s 3:00 AM. The pager goes off. You stumble out of bed, eyes barely open, and log in. Slack is screaming. The “Checkout Service” is returning 500s and your error budget is on fire. You open Cloud Logging. Then Cloud Monitoring. Then Jira. Then Github. You’re trying to mentally …Read more → -
🧠💻 The Neuro-Coder: A 6-Part Investigation into AI, Dopamine, and Developer Sovereignty
We need to talk about what AI is doing to our brains. For the last year, we’ve been obsessed with Benchmarks. Is Claude 3.7 better than GPT-5 (we all know its Gemini 😜)? Can it solve LeetCode Hard? Can it write a compiler in Assembly? But we forgot to benchmark the most important component of the …Read more → -
☕️🏗️ Git Worktree: The Architecture of the AI Conductor
In my previous research into the “Coder to Conductor” shift, I explored how we are moving from typing every bracket ourselves to orchestrating a symphony of AI agents. It sounds grand, doesn’t it? But when you actually try to do it on your laptop, the music stops pretty quickly. …Read more → -
🐢🛡️ The Neuro-Coder (Part 6): Designing the Casino (How to Tame the Machine)
This is Part 6, the finale of The Neuro-Coder. We’ve diagnosed the problem. Now, let’s fix it. So, here we are. We know the IDE is a Slot Machine (Part 1). We know we have biases (Part 2). We know it’s slowing us down (Part 3) and hurting our juniors (Part 4). The knee-jerk reaction is to say: …Read more → -
📉📊 The Neuro-Coder (Part 5): Beyond DORA (Why Velocity is Meaningless)
This is Part 5 of The Neuro-Coder. In Part 4, we looked at the human cost. Now, we look at the business cost. If you are an Engineering Manager using “Velocity” or “Lines of Code” to measure your team in 2026, stop. You are measuring noise. For decades, we’ve used proxies for …Read more → -
🧟♂️🧠 The Neuro-Coder (Part 4): The Human Cost (ADHD, Juniors, and Burnout)
This is Part 4 of The Neuro-Coder. In Part 3, we looked at the data. Now, we look at the people. The AI revolution isn’t affecting everyone equally. For a Senior Staff Engineer with 20 years of context, AI is a force multiplier. They know what to ask, and crucially, they know when the AI is …Read more → -
🎭🤖 Architecting Autonomy: Multi-Persona Environments in Gemini CLI
Picture this: You’ve just spent two hours deep-diving into a complex Rust memory leak with your AI assistant. It’s loaded with stack traces, cargo manifests, and the precise nuances of the borrow checker. Then, you switch tasks. You ask it to write a blog post about the experience. Suddenly, your …Read more → -
📉☕ The Neuro-Coder (Part 3): The Dopamine Gap (The Reality Check)
This is Part 3 of The Neuro-Coder. In Part 2, we looked at the biases that trap us. Now, we look at the data that exposes the cost. “AI makes me 10x faster.” We’ve all said it. We’ve all felt it. You prompt, the code appears, and you feel like you’ve just sprinted a marathon in a …Read more →
