What does this automation do?
An incoming webhook payload is unpacked, then handed to a saved agent command so the same runbook executes the same way every time.
What can you do with it?
- Trigger a runbook from any system that can post JSON
- Pull the fields you need out of the payload before anything reads it
- Run a reviewed command instead of an improvised prompt
The Steps
This automation runs in 4 steps:
- When HTTP — Webhook Received
- Then Utilities — JSON Extract (JSONPath)
- Then Taskade AI — Run an agent command ("Ops Runbook")
- Then Taskade — Add Task
What makes this different from a Zapier-style flow?
The "Ops Runbook" step is not a one-off model call. It is a Taskade AI agent that knows your services, runbooks and escalation paths, remembers every incident it has already worked, 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 engineering and on-call teams wiring their own systems in. An incoming webhook payload is unpacked, then handed to a saved agent command so the same runbook executes the same way every time.
How do you set it up?
- Open the "Automations" tab in your workspace.
- Click ➕ Add automation, then start from scratch.
- Add the trigger "Webhook Received" from HTTP.
- Add the action "JSON Extract (JSONPath)" from Utilities.
- Add the action "Run an agent command" from Taskade AI. Point it at an agent called "Ops Runbook".
- Add the action "Add Task" from Taskade.
- 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.