Features

One page per thing humanize does. Each says what it is, how to reach it from the prompt, from a command line and from Python, and what it will not do.

At the prompt

Being away (/afk)	Whether an agent may stop and ask you something.
Showing the working (/details)	Tool calls and thinking, or only what the agent says.
The shape of a run (/status)	Who is working, who handed to whom, what it cost.
Talking to a running turn	A line typed mid-turn goes into it, not after it.
Many conversations at once	One transcript, tab between the agents that are working.
Completion	What a half-typed line could become, under the editor.
History	Everything typed here before, on ↑ and ↓.
Exporting a transcript	/export writes what is on screen, as it was written.
What a project remembers	Reopening finds it set up the way you left it.
Stopping	esc ends the flow; what that does to a turn.

What an agent is

Efforts	How hard to think — and moving it while the flow runs.
Permissions	Four rungs, from read-only to bypass.
Skills	Which of a CLI's skills this agent is loaded with.
Goals	The backend's own goal feature: it decides when it is done.
Questions	An agent stopping mid-turn to ask its user something.
Answers in a shape	A turn that answers with a pydantic model instead of prose.
Hooks	Python callables hung on the moments of a turn.
Cost and rate	What has been spent, how fast, and how hard it is thinking.
The person as an agent	You, driven by a flow like any other agent.

Where the work lands

Providers	One CLI, two accounts, at the same time.
Containers	A container of the agent's own, up on the first turn.
Remote execution	The agent here; its commands on the build box.
Worktrees	One agent working in several directories at once.

What a run leaves behind

Flowverses	A git repository of flows, offered by name.
Tracing	The whole run as one timeline you can open in Perfetto.

---

Looking for the exhaustive list of flags and keys instead? CLI and TUI.