download dots

⚠️ Alert the Chat When a Comment Says Blocked with AI

Most comments stop the run. One that raises a blocker is read, summarized, sent to the chat, and pinned so it cannot be scrolled past.

  • Event-triggered
  • 100+ integrations
  • Branching logic
  • Schedule + monitor
UNIT · TASKADE.FLOW5 STEPS

How this flow runs

When

When someone comments

Taskade

Then 1

Filter

Continue only if the comment raises a blocker

Stop a run cleanly when a condition is not met. A filtered run is not a failure, so it never shows up as an error — inside a loop it skips just that item and keeps going.

Then 2

Agent

Escalation Watch

Ask an agent · Taskade AI

Knows
your dependencies and who owns each part of the system
Remembers
which blockers it has already raised in this chat

Then 3

Send Message

Telegram Bot

Then 4

Pin Message

Telegram Bot

This agent carries its knowledge and memory between runs, and can call your other automations as its own tools. How custom agents work

Filter is a step you add in the builder, in the same list as an app step — there is no separate scripting surface. All automation actions

Build this flow with AI

Opens the builder with these steps already described. Free to start, no card.

What does this automation do?

Most comments stop the run. One that raises a blocker is read, summarized, sent to the chat, and pinned so it cannot be scrolled past.

What can you do with it?

  • Escalate a blocker the moment someone writes it down
  • Skip the comments that need no escalation at all
  • Keep the blocker pinned until it is dealt with

The Steps

This automation runs in 5 steps:

  1. When Taskade — When someone comments
  2. Then Filter — continue only when the comment raises a blocker
  3. Then Taskade AI — Ask an agent ("Escalation Watch")
  4. Then Telegram Bot — Send Message
  5. Then Telegram Bot — Pin Message

What makes this different from a Zapier-style flow?

The "Escalation Watch" step is not a one-off model call. It is a Taskade AI agent that knows your dependencies and who owns each part of the system, remembers which blockers it has already raised in this chat, 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 delivery teams who discuss work in comments and live in chat. Most comments stop the run. One that raises a blocker is read, summarized, sent to the chat, and pinned so it cannot be scrolled past.

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 a Filter step: Filter — continue only when the comment raises a blocker.
  • Add the action "Ask an agent" from Taskade AI. Point it at an agent called "Escalation Watch".
  • Add the action "Send Message" from Telegram Bot.
  • Add the action "Pin Message" from Telegram Bot.
  • 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.

Related from the blog