What does this automation do?
Each message is judged against your rules by an agent that remembers who it has warned, then either removed with an explanation or answered.
What can you do with it?
- Enforce the rules consistently at any hour
- Explain a removal instead of deleting silently
- Answer the messages that deserve an answer
The Steps
This automation runs in 3 steps:
- When Telegram Bot — New Message
- Then Taskade AI — Ask an agent ("Moderator")
- Then Branch — Breaks the rules: Delete Message, Send Message · Worth answering: Send Message
What makes this different from a Zapier-style flow?
The "Moderator" step is not a one-off model call. It is a Taskade AI agent that knows your community rules and what counts as off-topic here, remembers which members it has already warned, 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 community managers running a large public group. Each message is judged against your rules by an agent that remembers who it has warned, then either removed with an explanation or answered.
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 Telegram Bot.
- Add the action "Ask an agent" from Taskade AI. Point it at an agent called "Moderator".
- Add a Branch step: Branch — Breaks the rules: Delete Message, Send Message · Worth answering: Send Message.
- 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.