What does this automation do?
When a public chat with your agent ends, a second agent writes the follow-up and files what the conversation could not answer.
What can you do with it?
- Turn a finished conversation into a follow-up someone owns
- Collect the questions your agent could not answer yet
- Tag the project so the gaps are reviewable as a set
The Steps
This automation runs in 4 steps:
- When Taskade — Agent Public Chat Ended
- Then Taskade — Send Message in Agent Chat ("Front Desk")
- Then Taskade — Add Task
- Then Taskade — Add Comment
What makes this different from a Zapier-style flow?
The "Front Desk" step is not a one-off model call. It is a Taskade AI agent that knows your pricing, onboarding and support pages, remembers the questions it could not answer 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 teams running a public agent on a site or in a community. When a public chat with your agent ends, a second agent writes the follow-up and files what the conversation could not answer.
How do you set it up?
- Open the "Automations" tab in your workspace.
- Click ➕ Add automation, then start from scratch.
- Add the trigger "Agent Public Chat Ended" from Taskade.
- Add the action "Send Message in Agent Chat" from Taskade. Point it at an agent called "Front Desk".
- Add the action "Add Task" from Taskade.
- Add the action "Add Comment" 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.