← All docs
Getting started
Your first sessionThe workspaceSSH access
Core concepts
Agent rolesExperimentsResearch plansCanvasWorkflows
Integrations
GitHubWebhooksNotifications
Platform
Billing and plansAgent memoryMulti-chatKeyboard shortcuts
Reference
GPU catalogAgent toolsAPI referenceSecurityLimits and quotas
← Docs
Getting started

The workspace

Layout

The workspace is a three-pane layout:

  • Left panel. File explorer, terminal output, GPU metrics. Toggle between tabs at the top.
  • Center panel. The main content area. Shows your canvas, experiment dashboard, or research plan depending on what you're working on.
  • Right panel. Chat. This is where you talk to the agent and see its responses and actions.

You can resize panels by dragging the dividers. Double-click a divider to collapse that panel.

File explorer

Shows the pod's filesystem. Click a file to preview it. Right-click to download, rename, or delete. The agent can also create and modify files. You'll see changes appear in real time.

Terminal

Live output from everything the agent runs. Commands, stdout, stderr. It's all here. You can scroll back through the full history. This is read-only; to run commands yourself, use SSH or ask the agent.

GPU monitor

Real-time GPU utilization, VRAM usage, temperature, and power draw. Updates every 2 seconds. Useful for spotting when a training run is actually using the GPU vs. being bottlenecked by data loading.

Switching tabs

Use the tab bar at the top of the left panel. Or use keyboard shortcuts:

| Shortcut | Action |

|---|---|

| Cmd+1 | File explorer |

| Cmd+2 | Terminal |

| Cmd+3 | GPU monitor |

| Cmd+E | Experiments panel |

| Cmd+/ | Focus chat input |

Keyboard shortcuts

Press ? anywhere in the workspace to see the full shortcut reference. Press Cmd+K to open the command palette, which lets you search for any action by name.

← Your first sessionSSH access →