Settings & Preferences

NimbleBrain organizes settings by scope — what each setting affects:

• You — your personal profile (theme, display name, timezone). Lives at /profile, reached from the avatar menu at the top-left of the sidebar.
• This Workspace — settings for the workspace you’re currently focused on (its name, members, instructions, app config, connectors, skills). Lives under /w/<id>/settings/*.
• Organization — admin-only settings that affect every workspace (model defaults, the workspace roster, user management, org-wide usage). Lives under /org/*.

Open profile or sign out from the avatar menu at the top-left. Open workspace and org settings from the workspace navigator and the workspace settings nav.

Your profile (/profile)

Reach your profile any time from the avatar menu at the top-left of the sidebar — click your avatar, then Profile settings. The profile surface is tabbed.

General (/profile/general)

• Display Name — how your name appears to teammates.
• Email — your login email (read-only).
• Role — your org-level role (read-only).
• Timezone — used for scheduling and time-related responses.
• Theme — System (follows your OS), Light, or Dark.

Click Save after making changes.

Skills (/profile/skills)

Your personal skills — prompt-composition guidance the agent picks up across all your workspaces.

The avatar menu also has a Sign out action.

This Workspace

This section reflects the workspace you’re currently focused on. Switch workspaces from the navigator at the top-left of the sidebar; the workspace settings update to match.

General (/w/<id>/settings/general)

• Workspace name — what shows up in the navigator and shared contexts.
• MCP Connection — your workspace ID, copyable. Use it when wiring up external MCP clients (Claude Desktop, VS Code, Cursor). Note that the /mcp endpoint is identity-bound and does not require a workspace header. See Connecting External Clients.
• Workspace Instructions — custom instructions injected into every conversation focused on this workspace, on top of any organization-wide policy. Workspace admins (or org admins/owners) can edit; everyone else reads.

Tip

Workspace instructions are great for team conventions: tone for shared documents, default triage priorities, citation policies. The agent picks them up on every turn — no need to repeat them in chat.

Members (/w/<id>/settings/members)

The list of who belongs to this workspace and their role. Membership for any workspace can also be managed by organization admins from Organization → Workspaces.

Apps (/w/<id>/settings/apps)

Per-bundle settings for the apps installed in this workspace. An app appears here only when its author registered a settings panel — otherwise the bundle has no settings UI to surface.

Some apps support custom instructions of their own — saved guidance the agent picks up whenever you’re using that app. When supported, the editor appears inside that app’s settings panel; the app owns storage and validation, and the platform includes the saved text in the agent’s system prompt on every turn. See the bundle-author docs for the other side of this.

Connectors (/w/<id>/settings/connectors)

Browse and configure the workspace’s connectors — point-and-click OAuth integrations and managed connectors. Install a connector here to make its tools available to the agent in this workspace.

Skills (/w/<id>/settings/skills)

The skills available in this workspace.

Organization (admin only)

Visible only to organization admins and owners. Hidden from regular members. These settings live under /org/*, outside any workspace URL.

Model (/org/model)

Choose which AI models the agent uses across every workspace:

• Default model — primary model for chat.
• Fast model — cheaper, faster model for quick auxiliary tasks.
• Reasoning model — most capable model for complex analysis.

Plus runtime limits — max iterations and max input/output tokens — and the Extended Thinking control.

The Extended Thinking modes are:

• Default — adaptive for reasoning models, off otherwise.
• Off — never reason.
• Adaptive — the model decides per call.
• Enabled — always reason. Enabling this reveals a Thinking Budget Tokens field (minimum 1024), which counts toward Max Output Tokens.

Reasoning is billed as output tokens, and the agent’s reasoning shows up in chat as a collapsible Thought chip. See Chat.

Caution

Model configuration is platform-wide. Changes affect every workspace and every user immediately. Restrict to org admins/owners.

Workspaces (/org/workspaces)

The org-wide workspace roster. Click into any workspace to manage its members, view its bundles, and see its metadata. Workspace creation, deletion, and cross-workspace member management live here.

To edit a specific workspace’s name or instructions, switch into it via the navigator and use This Workspace → General.

Users (/org/users)

Manage user accounts at the organization level — change someone’s org role or remove a user.

Usage (/org/usage)

Organization-wide usage analytics:

• Cost over time — spending across a chosen period.
• Token breakdown — input, output, and cache usage.
• Model usage — which models the agent is using and what each costs.
• Activity stats — LLM calls, response times, conversation counts.

Note

Usage is reported at the organization level only. There is no per-workspace usage tab.

Custom-instruction layers

Custom instructions stack from broad to narrow, and the agent reads them on every turn:

1. Organization policy applies everywhere.
2. Workspace Instructions (This Workspace → General) layer on top for the focused workspace.
3. App custom instructions (This Workspace → Apps) apply when you’re using that app.

Sidebar layout

The sidebar collapses with the toggle on its right edge (or ⌘B / Ctrl-B). Collapsing hides labels but keeps icons; expanding restores the full nav. Your avatar and the workspace navigator sit at the top-left; clicking the avatar opens a popover with Profile settings and Sign out.