I published The Two Extremes of AI-Assisted Engineering: Fast and Furious, vs. Slow and Careful, about the two opposite ways I work with the same coding agents: letting them run while I barely read the code, and slowing down until every decision is mine. It uses EDControlRoom as the example of a project moving along that spectrum, and argues that the real decision is where to set the quality bar for each project right now, and when to move it. This is the third version; I wrote it section by section after setting two earlier drafts aside.
I use the same coding agents in two opposite ways: fast and furious,
where I barely read the code and have made 10,000+ commits in the last
12 months, vs. slow and careful, where every decision is mine. Neither
is right. The real decision is where to set the quality bar for each
project, right now, and when to move it.
I published Start the Chain: My Three-Agent Setup Is Now One Command, a follow-up to the main agent post. The main agent, secondary and worker setup is now the agent-chain skill in tmux-agents, started with one command, and the post covers what changed with a week of real use and how projects talk to each other. It also covers what happens after a restart: tmux-main-sequence brings back a chain for every project, and /resume brings back the conversations that matter.
The main agent, secondary and worker setup I pieced together by hand is now
built into tmux-agents. One command starts the chain, a script starts one for
every project after a reboot, and /resume brings back the conversations.
I published How To Move Fast and NOT Break Things with AI, about the point where using an agent's name as its id stopped fitting tmux-agents. It covers the move to real ids in progress for v1.9.0, and the tests, decision records and release rules that grew out of real use. The lesson is to prototype fast, then add structure where the problems show up and leave guard rails for the next agent.
Move fast with AI, and add proper engineering when real usage shows you
need it. For tmux-agents, that meant letting each agent's name double as
its id, until it couldn't, and then adding real ids and guard rails so
the agents and I don't repeat the mistake.
I published Your Sub-Agents Shouldn't Disappear: Meet tmux-agents, the introduction to tmux-agents that my last two posts kept pointing back to. It covers why I wanted visible sub-agent sessions, how I use them on my game and this blog, and how to try the tool. I also wrote down a few of the design choices and the limits I'm still working through.
Built-in sub-agents hand you a summary and the work behind it is gone.
tmux-agents gives every delegated task its own Claude or Codex session in
a tmux pane instead, so you can watch it, step in, and pick its
conversation up later.