15 posts across 4 themes
AI-First Development
I build software by directing a team of AI agents rather than typing most of the code myself. This page collects everything I have written about that shift, organised by theme rather than date. Start with the journey posts if you are new to the idea, or jump straight to the setup and patterns if you want the practical detail.
Start here
The journey posts: how I went from Copilot autocomplete to orchestrating agents, and an honest account of six months working this way.
- From Copilot to Conductor: My AI Development JourneyMy path from basic GitHub Copilot autocomplete to full AI-first orchestration wasn't planned. It was a series of realisations about what was actually slowing me down.20 Feb 20264 min read
- Why I Stopped Writing Code and Started Orchestrating AI AgentsI no longer write code directly. Instead, I manage a team of AI agents that do the implementation while I stay free to think, redirect, and make decisions in real-time.28 Mar 20265 min read
- Practical Lessons from Six Months of AI-First DevelopmentSix months of building software primarily through AI agents. Here's an honest account of what works, what doesn't, what surprised me, and what I'd tell teams considering the switch.15 Jan 20267 min read
The setup
The tooling that makes the workflow safe and observable: my published Claude Code configuration, the git hooks that guard unsupervised agents, custom status lines, model routing, and running it all from a phone.
- The Claude Code Power Setup That Changed How I Build SoftwareI published my complete Claude Code configuration as a gist - Team Lead Mode, 8 slash commands, model routing, hooks, and more. Here's what's in it and why it matters.20 Mar 20265 min read
- 11 Git Hooks That Make AI Agents Safe to Run UnsupervisedAI agents can write code fast, but speed without guardrails is dangerous. Here are the 11 hooks I use to make sure my agents never commit secrets, skip formatting, or break conventions.8 Mar 20266 min read
- Building Observable AI Workflows with Custom Status LinesWhen AI agents do your development work in the background, you need observability. Here's how I built a custom status bar that shows me everything I need at a glance.12 Feb 20265 min read
- Model Routing: Why I Use Different AI Models for Different TasksUsing the most powerful AI model for every task is like driving a lorry to the corner shop. Here's my model routing strategy and why it improves both speed and quality.5 Feb 20264 min read
- Claude Code in My Pocket: Building cc-remoteAt the end of my Split writeup I said the next iteration of this lifestyle wasn't a nicer office on the road - it was no office. cc-remote is the first real step: a Claude-branded Android chat client driving persistent Claude Code sessions in tmux on a Raspberry Pi 5, over Tailscale. Full-fat Claude Code, on my phone, no laptop required.6 Jul 20266 min read
The pattern
The core working model: treating AI as a team of specialists with a manager coordinating them, and having two instances review each other's code.
- The Manager Pattern: Treating Your AI Like a Development TeamThe most effective way to use AI for development isn't as a single assistant - it's as a team of specialists with a manager coordinating their work. Here are the patterns that make it work.28 Jan 20265 min read
- How Two AI Instances Review Each Other's CodeI built a system where two Claude Code instances review PRs through a Slack thread, discussing trade-offs back and forth and automatically committing fixes. Here's how it works.28 Feb 20264 min read
In practice
What the workflow changes day to day: the staff engineer's role, why the async manager pattern suits remote life, and month-long stints shipping from Lisbon, Rome, and Split.
- Staff Engineering in the Age of AI: What Actually ChangesAI doesn't replace the staff engineer - it amplifies the parts of the role that matter most. Architecture, system design, mentoring, and high-leverage decision-making become even more important.14 Mar 20264 min read
- Why AI-First Development is Perfect for Digital NomadsThe manager/agent pattern is inherently async - spawn work, go live your life, come back to results. AI-first development and the nomad lifestyle are a natural fit.1 Apr 20267 min read
- Coding From Lisbon: A Month of AI-First Development on the Road28 days working remotely from Lisbon - how the AI-first manager pattern, a travel router, and a good routine made it one of my most productive months yet.3 Apr 20267 min read
- Coding From Rome: Ancient City, Modern WorkflowA month of remote work from Rome - where world-class history is a 20-minute walk from your desk, but the local cafes want you in and out. Here's how the AI-first workflow held up against API rate limits and Italian work culture.4 May 20265 min read
- Coding From Split: A Villa, a Pool, and a Cat Who Kept Letting Himself In30 days working remotely from Kastela, on the Dalmatian coast just outside Split. A private villa with a roof terrace, calm water minutes away, and a workflow that mostly held up - but also started giving me ideas about how to untether even further from the desk.25 May 20268 min read