What does this automation do?
A message in the incident channel is graded for severity, logged as an incident, and escalated when it clears your threshold.
What can you do with it?
- Grade severity the moment the message lands, not at standup
- Escalate only what clears the threshold you wrote down
- Keep the grading rationale attached to the incident record
The Steps
This automation runs in 4 steps:
- When Slack — New Message
- Then Taskade AI — Ask an agent ("Incident Commander")
- Then Taskade — Add Task
- Then Slack — Send Channel Message
What makes this different from a Zapier-style flow?
The "Incident Commander" step is not a one-off model call. It is a Taskade AI agent that knows your severity matrix and escalation ladder, remembers every incident it has graded before, so every run builds on the last one instead of starting from an empty prompt.
A stateless "ask the model" step forgets everything the moment it returns. An agent keeps its knowledge and its memory between runs, carries its own tools, and can be handed work by other automations.
Who is this automation for?
Built for on-call and support engineering teams. A message in the incident channel is graded for severity, logged as an incident, and escalated when it clears your threshold.
How do you set it up?
- Open the "Automations" tab in your workspace.
- Click ➕ Add automation, then start from scratch.
- Add the trigger "New Message" from Slack.
- Add the action "Ask an agent" from Taskade AI. Point it at an agent called "Incident Commander".
- Add the action "Add Task" from Taskade.
- Add the action "Send Channel Message" from Slack.
- Enable the toggle in the top-right corner to activate the automation.
Prefer to describe it instead? Click Build this flow with AI above and Taskade wires the trigger, the steps, and the agent for you.