// docs

Skills & Guardrails

Skills are the agent's hands. Approvals and scopes are the leash — you decide exactly what S.E.N.T.R.I can touch.

Built-in skills

These skills are always available to the agent:

SkillWhat it does
AutomationCheck the dashboard for job status/IDs; restart or cancel jobs.
Plan ExecutionCheck the current time and schedule a runbook for a host.
Check AvailabilityPing hosts or check whether a specific port is open.
Check EventsRead recent Application, System, or Security events from a host.
Check LogsPull the most recent ServerEngine log entries.

Optional skills

Enable these in Settings when you need them (some require credentials or an API key):

SkillWhat it does
Admin ModeOpen a PowerShell session to a host and run commands interactively.
Active DirectorySearch users and groups, read user info, and list group/department members.
HypervisorManage virtual machines on Proxmox VE and VMware ESXi.
Web SearchSearch the web and fetch page content (Brave-powered — bring your key).
Slack MessagePost messages to up to three Slack channels.
JiraCreate/read tickets and subtasks, transition status, comment, list your tickets.
ConfluenceCreate, read, and update Confluence pages.

Custom skills from runbooks

Turn any runbook into a skill S.E.N.T.R.I can call. Give it a description and an optional parameter, and the agent can trigger the whole workflow from a natural-language request.

Approvals

Mark any skill as approval-required. When the agent wants to run it, ServerEngine pops a confirmation showing the exact skill and host and waits for you to Accept or Decline before anything executes. Decline, and the agent is told you refused and moves on.

Approvals need a human at the console

Approvals apply to interactive chat only. A scheduled prompt or an API-triggered Prompt job runs headlessly with no one to ask, so approval-required skills are skipped on those runs. Scope tightly and disable what an unattended run should never touch.

Scopes

A scopeis an allow-list of hosts. Build it from your server groups to define exactly which machines S.E.N.T.R.I may act on. The agent is only ever shown the hosts in the current scope and is instructed to use nothing else — so it can't wander outside your boundary.

Layered control

Combine the three: disable skills you don't want available, require approval on the risky ones, and scope the agent to a safe set of hosts. You get autonomy where it helps and a hard stop where it matters.

Admin Mode safeguards

Admin Mode grants full PowerShell access to a host. ServerEngine guards against overlapping sessions so two connect requests can't race, and every action still respects your approval and scope settings.