What does this automation do?
When a comment lands on a task, an agent that has followed the whole account replies in context instead of asking what happened before.
What can you do with it?
- Answer a follow-up without re-reading three months of thread
- Keep one continuous account history the whole team can see
- Show what long-term agent memory actually looks like in a live flow
The Steps
This automation runs in 3 steps:
- When Taskade — When someone comments
- Then Taskade AI — Ask an agent ("Account Historian")
- Then Taskade — Add a comment
What makes this different from a Zapier-style flow?
The "Account Historian" step is not a one-off model call. It is a Taskade AI agent that knows every project, document and thread in the workspace, remembers the full history of this account, 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 account and project managers running long threads. When a comment lands on a task, an agent that has followed the whole account replies in context instead of asking what happened before.
How do you set it up?
- Open the "Automations" tab in your workspace.
- Click ➕ Add automation, then start from scratch.
- Add the trigger "When someone comments" from Taskade.
- Add the action "Ask an agent" from Taskade AI. Point it at an agent called "Account Historian".
- Add the action "Add a 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.