Use the assistant

Ask questions about your workspace, get taken to the right screen, or let the assistant take an action — after you approve it. It works with your permissions, so two people can ask the same question and get different answers.

Where to find it:

• Header → Ask AI (starts with a question about the page you’re on)
• Keyboard shortcut ⌘⇧A (Ctrl+Shift+A on Windows and Linux) — toggles the side panel
• Sidebar → Agent — same panel toggle; open /assistant for the full-page view

Panel vs full page

Both share the same conversations, models, and approvals.

Ask it something

Type a question and send it. Useful prompts:

• “How do I connect Slack?”
• “What does this toolbox share, and with whom?”
• “Take me to my connections”
• “Why can’t I see the governance section?”

Mention toolboxes, connections, or connectors with @ when you want to point at a specific resource. Attach a file or screenshot when showing is easier than describing.

Slash commands

Type / in the composer for starters:

The picker ranks the commands that fit the page you are on first.

Approve what it does

When the assistant wants to change something, it shows an Approval needed card with exactly what it’s about to do. Nothing runs until you choose:

flowchart TD
  Ask["You ask the assistant"] --> Plan["Assistant proposes an action"]
  Plan --> Gate{"Needs approval?"}
  Gate -->|No| Run["Action runs"]
  Gate -->|Yes| Card["Approval needed card"]
  Card --> Once["Allow once"]
  Card --> Always["Always allow<br/>non-destructive only"]
  Card --> Deny["Deny"]
  Once --> Run
  Always --> Run
  Deny --> Stop["Action stopped"]
  Run --> Audit["Audited"]

Always allow is never offered for destructive operations. Remembered approvals are enforced server-side and audited. Approving never widens your access: each action is still checked against your own permissions, so anything your role can’t do stays blocked.

Models and organization keys

If your organization has configured providers under Settings → Assistant, you can pick a model from the allowlisted catalog (grouped by provider). Providers without an organization key remain visible but disabled.

API keys are organization bring-your-own-key (BYOK) — administrators paste Anthropic, OpenRouter, Fireworks, or OpenAI-compatible gateway credentials in settings. Chat does not use personal keys in the browser. Availability depends on that configuration; see Configure the assistant.

A context meter shows how full the conversation is (green / amber / red). Use /compact or start a new chat when it fills up.

Permissions

Built-in Member and above can use the assistant. Guest and Auditor can’t — neither holds tool:execute. Managing providers needs Manage assistant (typically Org Admin / Owner).

Manage conversations

• New chat when you change subject — context is per conversation
• Conversation switcher for history (searchable, grouped by recency)
• Rename or delete threads you no longer need
• Edit the last message to truncate and retry from there when the UI offers it

Good to know

• The assistant respects your role, shares, and restrictions the same way the rest of the app does.
• After successful changes it may navigate, refresh lists, or open the right dialog — still within allowlisted UI commands.
• Model choice and whether the assistant is available depend on Assistant settings.

Related

• Configure the assistant
• Getting around
• Roles and permissions
• Set restrictions