Notes on my process

Building with AI

I learned to code without it, ignored it for years, then went all in. This is how I build now.

How I got here

  1. PDFs

    Before AI

    I learned to code before any of this existed. No assistants and not much material either, mostly PDFs I had to dig through on my own. Tough as a kid, but it taught me how to learn.

  2. GPT-3

    First contact

    GPT-3, while I was moving from React to Next.js. It invented imports and got the framework wrong. I decided AI could not code.

  3. Study

    University

    It earned a place as a study partner. Pass in a textbook, talk it through, go back and forth. Good for digesting material, nothing more.

  4. Cursor

    Early 2025

    Cursor started building whole features from plain English. Work that took me hours, done in minutes. I had ignored it too long, so I did what I do with any new skill: went all in.

  5. T3 Code

    Today

    A local MCP server, a small software factory that automates most of my work, custom tools around my workflow, and voice agents.

Current stack

The subscriptions I'm running right now.

Claude Code logo

Coding agent

Claude Code

Codex logo

Coding agent

Codex

OpenCode logo
+
DeepSeek logo

OpenCode with DeepSeek V4.1

Backup for token-heavy jobs.

Manuel MCP

A local MCP server holding the repeatable jobs I ask my agents to do. I built it because I needed it, not for anyone else.

Most of it exists as skills too. The MCP wins because any coding agent picks it up, whatever the model or the agent.

manuel
mcp
  • Read my email
  • Send email
  • Automated emails
  • Identity service lookups
  • Speak out loud
  • Snip and annotate

How it grows

  1. I ask an agent to do the job
  2. Slower, more tokens, but it gets done
  3. The job comes back again
  4. It becomes a tool in the MCP

Then the next job starts the loop again, and the server keeps getting bigger.

How my setup evolved

From a bare terminal to a bench of agents.

  1. Then · The CLI

    Claude Code
    ~ $ claude
      no CLAUDE.md
      no skills
      default everything
    
    > build the booking page
      Writing BookingPage.tsx
    > no, use the existing form
      Rewriting BookingPage.tsx
    > still wrong, start again
      ...
    Claude Code in a bare terminal. Default settings, no skills, nothing configured.
  2. Next · Skills

    • RPI Research, plan, implement
    • TDD Tests first, then code
    • Matt Pocock's skills
    • My own skills Written as the work repeats

    Then I learned about skills. My agents started following a process instead of improvising.

  3. Now · T3 Code

    T3 Code app icon

    T3 Code

    Every agent, one window.

    • Claude Code logo Claude Code Several subscriptions
    • Codex logo Codex Several subscriptions
    • OpenCode logo OpenCode Backup for token-heavy jobs
    Orchestrator v2AutomationsManuel MCPVoice agents

    Several Claude Code and Codex subscriptions run side by side, with OpenCode as the backup for token-heavy jobs. Orchestrator v2 coordinates them, and a lot of the routine runs as automations.