Anthropic engineer nailed it:

"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."

This is one of the best engineering workflows I've seen in a long time.

In a recent presentation, Anthropic's Daisy Hollman broke down exactly how their internal teams deploy Claude Code at scale.

She exposed the huge difference between how most people use Claude, and how its creators use it:

→ The token bloat that cripples your prompt before you type a word

→ The automation workflows most users don't know exist - like Routines

→ The daily task pipelines that run without touching the keyboard, using the Claude /goal

 → The exact workflows Anthropic's own engineers automated first, using Git worktrees to run multiple Claude instances simultaneously without collisions.

If you've been using Claude for more than a month and never left the chat window, you've been using one agent.

When you could be running a team of them.

Instead of another show, watch this talk.