What does this automation do?
A question in Slack is answered from your own handbook by an agent whose knowledge is your documentation, not the open internet.
What can you do with it?
- Answer from your handbook instead of from a generic model
- Cut the interruptions that land on the one person who knows
- Surface the questions people keep asking, so the docs can be fixed
The Steps
This automation runs in 3 steps:
- When Slack — New Message
- Then Taskade AI — Ask an agent ("Docs Desk")
- Then Slack — Send Channel Message
What makes this different from a Zapier-style flow?
The "Docs Desk" step is not a one-off model call. It is a Taskade AI agent that knows your handbook, runbooks and product documentation, remembers the questions people keep asking, 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 internal teams that keep answering the same question. A question in Slack is answered from your own handbook by an agent whose knowledge is your documentation, not the open internet.
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 "Docs Desk".
- 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.