What does this automation do?
An agent reads each new document, works out who should look at it, and the review lands as an assigned task rather than a message somebody misses.
What can you do with it?
- Route a document by what it says, not by which folder it landed in
- Cut the delay between a document appearing and someone reviewing it
- Keep the routing reasoning on the task for later
The Steps
This automation runs in 5 steps:
- When Google Docs — New Document
- Then Google Docs — Read Document
- Then Taskade AI — Ask Agent ("Review Desk")
- Then Taskade — Add Task
- Then Taskade — Assign Task
What makes this different from a Zapier-style flow?
The "Review Desk" step is not a one-off model call. It is a Taskade AI agent that knows what each reviewer looks for and which topics they own, remembers how earlier documents of the same kind were routed, 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 teams with a review queue and no routing rules. An agent reads each new document, works out who should look at it, and the review lands as an assigned task rather than a message somebody misses.
How do you set it up?
- Open the "Automations" tab in your workspace.
- Click ➕ Add automation, then start from scratch.
- Add the trigger "New Document" from Google Docs.
- Add the action "Read Document" from Google Docs.
- Add the action "Ask Agent" from Taskade AI. Point it at an agent called "Review Desk".
- Add the action "Add Task" from Taskade.
- Add the action "Assign 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.
