Ask, Plan & Auto modes
The three AI copilot modes in Servor — Ask for read-only advice, Plan to approve every action, Auto to run hands-off — and when to use each.
The AI copilot always works through a single tool, run_command. What changes between
sessions is how much it's allowed to do on its own. That's the mode. You pick one
at the top of the chat before (or during) a session, and you can switch at any time —
open a server in Servor and switch to its AI tab
to try it.
| Mode | What it does | Best for |
|---|---|---|
| Ask | Read-only. Advises and explains, never changes anything. | Learning, second opinions, safe investigation. |
| Plan | Proposes each command; you approve every one before it runs. | Careful changes where you want a look at each step. |
| Auto | Runs commands on its own — except destructive ones, which still need your approval. | Routine, low-risk work you don't want to babysit. |
One rule never changes
Whatever the mode, risky and destructive actions always require your approval. Auto doesn't skip that — it only removes the approval prompt for the safe, routine commands. See Approve actions.
Ask — read-only advice
In Ask mode the copilot won't change anything on your server. It can still read context — check a service, tail a log, look at disk usage — but it uses that only to answer your question and suggest what to do next. Nothing it proposes gets applied.
Use Ask when you want to:
- Understand a problem before touching anything ("why is my site slow?").
- Get a recommended fix you'll apply yourself in the web terminal.
- Learn how something on the server is configured.
Think of it as a knowledgeable colleague looking over your shoulder — full of advice, hands in their pockets.
Plan — approve every action
Plan is the careful middle ground, and a good default. The copilot works out what needs to happen and proposes commands one at a time. Each one waits for your approval before it runs. You see exactly what it wants to execute, approve it (or skip it), and the copilot reads the result before deciding the next step.
Use Plan when you're making real changes but want to keep a hand on the wheel — a config edit, a service restart, anything on a production box you care about.
Not sure which mode?
Start with Plan. You get the copilot's full problem-solving, and nothing runs without you seeing it first. Move to Auto once you trust the task.
Auto — hands-off, with a safety net
In Auto mode the copilot runs safe commands on its own and keeps going, showing you results as it works. It's the fastest way through routine, repetitive work. The safety net stays on: anything risky or destructive still pauses for your approval, exactly like in Plan. Auto only removes the prompt for the low-risk commands.
Use Auto for:
- Routine health checks and diagnostics.
- Multi-step read-heavy work where approving each step would just be clicking "yes".
- Tasks you've done before and trust the copilot to handle.
Auto still can't run everything
Auto never runs a blacklisted command (Servor blocks
known-dangerous commands like rm -rf / for everyone), and it never runs a
destructive action without asking. If a session goes quiet waiting on you, it's
almost always an approval prompt.
Switching modes mid-session
You can change modes at any point in a conversation. A common flow:
Start in Ask to understand
Let the copilot investigate and explain the problem without changing anything.
Move to Plan to fix carefully
Switch to Plan and approve each command as the copilot applies the fix.
Drop into Auto for the routine tail
Once the risky part is done, switch to Auto to let it finish the repetitive checks on its own.
How modes relate to roles
The mode controls the copilot; your role controls whether you can use the copilot at all. Viewers can't run commands, so they can't start a session in any mode. Members, admins and owners can. See Roles and permissions.