Starting and steering agents
5 min read
This page covers the two verbs of the board: starting an agent session and steering it while it runs - answering questions, queueing the next task, and stopping it when it goes down the wrong path.
Start a new session
Open the New Session dialog
Click New Session in the toolbar (or press Ctrl+N). The dialog also has tabs for Named Sessions and Resume Session - more on those below.
Pick the agent
The agents you have configured appear as a row of choices, with the first one preselected. Claude Code and Pi ship with verified drivers and are always available; you manage the list under Settings - Agents. Choosing Custom CLI lets you point the session at any command-line tool by giving its command and arguments.
Pick the repository
Choose the folder the agent will work in - the dialog lists the repositories you have used, sortable by name, path, or last used, and a Browse button picks any folder. The agent edits real files in that folder, so for a first run start somewhere low-stakes.
Decide about permission prompts
Bypass permission prompts is checked by default: the agent works without stopping to ask before each tool action. Uncheck it if you want to approve actions as they happen - the session's card will flip to Permission each time the agent wants a decision.
Start
A new card appears on the board and the agent launches in its terminal. Give it the first task from the prompt bar - or set the task up front with a named session.
Named sessions and resuming
Named Sessions are saved presets - a repository plus an agent under a name you choose, launched with one click. Save any running session as a named session from its card menu. Resume Session lists your past Claude Code conversations with a summary, message count, and how long ago they ran, and picks one up where it left off - the way back after you close a session or restart the app.
The prompt bar
- Send (Ctrl+Enter) - type a message and send it into the terminal.
- Queue (Ctrl+Shift+Enter) - add the message to the session's queue instead of interrupting; it is delivered when the agent is ready for it.
- Speak (Ctrl+H) - dictate instead of typing. See voice.
- Expand - open a large editor for long prompts, with image preview for screenshots you attach.
- Explain - have DevThrottle read the session and tell you what is happening in it - useful when you come back to a wall of terminal output.
Stop, interrupt, and clear
The action bar above the terminal gives you graduated brakes:
- Stop - the agent's own soft cancel (Esc). Ends the current turn; the conversation continues.
- Interrupt - a hard interrupt (Ctrl+C), stronger than Stop, for when the agent will not let go.
- Clear context - reset the conversation in place while the process keeps running - a fresh start without a new session.
- History - open the agent's in-terminal history picker to jump back to an earlier point.
The action bar also shows a context-window gauge - how full the agent's working memory is - which is your cue to clear context or wrap up the task.
Answering an agent
When a card turns red, click it, read the question in the terminal, and answer in the prompt bar. If the card shows Permission, the agent is asking to run a specific action - approve or deny it right in the terminal. Then get out of the way; the card goes blue and you go back to whatever you were doing.
The card menu
The "..." menu on each card: Rename, Hold / Take Off Hold, Open in Explorer, Open in VS Code, Save as named session, and Close Session.