How AI Agents Made Me CLI-First

I used to sit on Safari checking gold prices. Bookmarks open, tabs multiplying, clicking around the page for the number I needed. Now I type goldcli price --today and the answer is there in a second. That one thing started a cascade. I started asking: what else am I doing in a browser that I could do from here?

The answer turned out to be most of my job.

AI agents are the reason. They live in the terminal. They read and write files, run commands, open PRs. To work with them effectively, I needed to meet them there. And the more I did, the more I realised the terminal is not just where the agents live. It is the better place to work full stop. No clicking, no context switching, no "can I automate this?" The answer is always yes, because everything is a command.

This shift from browser to terminal changed how I build software. I wrote about the workflow that came out of it in a separate article called How I Build Software With Agent Loops. This one is about why the terminal became the centre of everything.

CLI-First is the Side Effect

Every tool in my workflow has a CLI interface. opencode. gh. git. td for Todoist. goldcli. Everything is a command.

The terminal is the universal adapter for agents. An agent cannot open a browser and click around. But it can run a command, parse the output, and act on it. When your workflow lives in the terminal, every part of it is automatable. There is no seam where a human has to step in because the tool requires a GUI.

This is the side effect I did not expect. I started using agents in the terminal because that is where they work. I stayed because the terminal is genuinely better. Faster. More composable. More scriptable.

The browser is the default for most people. The terminal is becoming the default for me.