Working in a session

Select a session in the rail and its page opens on the right. This is where you watch what an agent is doing and steer it - the same controls you have on the desktop Director, in a browser tab. The page has three tabs across the top, an action bar, and a message box at the bottom.

Three ways to follow a session

The Terminal, Chat, and Voice tabs are three views of the same live session - reading, not three separate things. Switching tabs never disconnects the session: the live connection stays open in the background, so you can move between them without dropping a beat.

Terminal

The Terminal tab is the live terminal, mirrored exactly as it looks on the machine running the agent - the raw, plain terminal, character for character. It is the ground truth: whatever the agent's command-line tool prints, you see here.

Chat

The Chat tab is the same conversation, cleaned up and made readable: the agent's replies and your prompts as chat bubbles, with Markdown rendered so lists, code, and emphasis look right. It updates live as the agent works. A Show: filter lets you reveal the parts that are hidden by default - Tool calls, Results, and Thinking - so you can read just the conversation, or open up every step the agent took.

Voice

The Voice tab is Wingman - a hands-free way to keep up with a session without watching the screen. Turn Wingman on and it narrates every completed turn as spoken audio, summarizing what the agent decided and did in plain language, so you can step away and still follow along. When a turn is ready, a small player lets you play and pause, restart, or seek through it, and a Respond button lets you answer back by voice instead of typing.

The action bar

Below the session sits a row of controls for the agent itself:

• Stop - halt what the agent is doing now.
• Interrupt - cut in while it is working to add or change direction.
• Clear context - start the conversation fresh without closing the session.
• History - read back the earlier conversation for this session.

These are the same steering controls documented for the desktop board under starting and steering agents - they behave the same way from the Cockpit.

The message box

At the very bottom is the composer, where you talk to the agent. It has four actions:

• Send - send your message to the agent now (Ctrl+Enter also sends).
• Speak - open the dictation dialog and talk your message straight into the box instead of typing it. This is the same dictation used everywhere in DevThrottle, and it runs through your Gateway on one shared path - so it behaves the same on desktop, in the browser, and on your phone. See Voice.
• Queue - add the message to the session's prompt queue instead of sending it right away (Ctrl+Shift+Enter queues). Queued prompts run in order as the agent frees up.
• Attach - add an image. The Cockpit uploads it from the device you are on to the machine the session runs on, saves it there, and inserts the saved path into your message so the agent can open it. Pasting an image into the box and dragging one onto it do exactly the same thing.

The dock

On the right of the session page is a dock with two panels:

• Queue - the session's prompt queue: the prompts waiting to run, in order.
• Screenshots - a gallery of the images attached to this session, so the pictures you have handed the agent stay in one place.

The session menu

The three-dot menu at the top right of the session page is the same session menu that sits on each rail card: Rename, Put on hold or Resume, Handover info, and Close session.

Where to go next

• The Fleet Map - step back and see the whole fleet as a map.
• Answering agents remotely - the practical away-from-your-desk flow.