What does this automation do?
An inbound webhook starts a chain: the agent decides which automation runs next, runs it, and files the result as tracked work.
What can you do with it?
- Chain several automations behind one webhook
- Let the next step be chosen from the payload, not hardcoded
- Keep a task record of every chain that ran
- Add a step to the chain without rewriting the caller
The Steps
This automation runs in 4 steps:
- When HTTP — Webhook Received
- Then Taskade AI — Ask an agent ("Chain Runner")
- Then Taskade — Run Automation
- Then Taskade — Add Task
What makes this different from a Zapier-style flow?
The "Chain Runner" step is not a one-off model call. It is a Taskade AI agent that knows your automations and what each one expects, remembers which chains completed and which failed, 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 ops teams wiring systems together. An inbound webhook starts a chain: the agent decides which automation runs next, runs it, and files the result as tracked work.
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 "Ask an agent" from Taskade AI. Point it at an agent called "Chain Runner".
- Add the action "Run Automation" from Taskade.
- 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.