Skip to content

Act · Automations

From alert to verified fix, on a graph you can read.

Build workflows by dragging nodes onto a canvas: trigger on an alert, run checks and commands on devices, branch, notify — and let an AI node write its assessment straight onto the alert.

Automations / Workflows
Example
Example: the workflow “BGP peer down — remediate” runs after an alert on core-rtr-01. It checks the peer, bounces interface Gi0/1, verifies the session is Established, comments on the alert and emails on-call. Run #142 succeeds in 9.4 seconds, with a timing on every node.

Workflow editor

Every step visible. Every branch explicit.

Alert triggers, remote commands and checks on devices, if/else branching, email and alert comments are nodes on a drag-and-drop graph. Today’s flows include “BGP peer down → check peer → bounce the interface → verify → comment → email”.

  • Alert triggers
  • Remote commands and checks on devices
  • If / else branching
  • Email and alert comments
Automations / Workflow editor
Example
Example: in the workflow editor, an AI Alert Insight node is dragged from the node palette onto the canvas and connected. The flow runs: device temperature alert, gather readings, then an if/else on temperature above 70°C; at 74°C the yes path runs AI Alert Insight and comments on the alert, while the no path (comment: within range) is skipped.

AI Alert Insight

An assessment on the alert before anyone opens it.

The AI node reads the alert plus live context and writes an assessment, a likely cause and next steps back onto the alert. Example: device temperature alert → gather readings → AI Alert Insight → comment on the alert.

Network Insights / Alert detail
Example
Example: on the alert “Device temperature high” for dist-sw-03 at 74°C, the AI Alert Insight node reads the temperature trend and fan speeds, then writes an automated comment: inlet temperature rose 9°C in 40 minutes while fan 2 reports 0 RPM; suspected cause fan 2 failure; next steps to check the fan, inspect airflow at rack B4 and replace the fan tray if confirmed. It suggests only; people and approved automations act.

Execution history

Every run, every node, every millisecond.

Each run is recorded with per-node timing and output, so you can see exactly what an automation did, in what order, and what it found.

Automations / Execution history
Example
Example: execution history for the workflow “BGP peer down — remediate”. Run #142 succeeded in 9.4 seconds; its timeline shows each node’s duration (bounce interface Gi0/1 took 4.6 seconds) and the Verify node’s show bgp summary output, with the peer Established. Run #140 failed at Verify.

Capabilities

Everything in Automations

The complete list, as it exists in the product today.

Workflow editor

  • Drag-and-drop node graph
  • Alert triggers
  • Remote commands and checks on devices
  • If / else branching
  • Email and alert comments
  • An AI node that reads the alert plus live context and writes an assessment, likely cause and next steps back onto the alert

Runs

  • Execution history for every run, with per-node timing and output

Example flows that exist today

  • BGP peer down → check peer → bounce the interface → verify → comment → email
  • Device temperature alert → gather readings → AI Alert Insight → comment on the alert

Coming soon

  • AI-authored automations

On the roadmap, not yet available.

Works with AI Core

Automations put AI Core on the alert.

The AI Alert Insight node brings AI Core’s reading of the situation into the workflow: an assessment, likely cause and next steps, written where the on-call engineer will see it. People and approved automations act; the AI explains and suggests.

How AI Core works

From Automations

  • AI Alert Insight node
  • Comments written back to the alert

Get started

See every signal in one place.

Start with one site and one probe. Add modules as you go — the AI Core gets more useful with every source you connect.

Already have an account? Sign in to the portal